2023-07-07 00:05:22,997 -        meta learning: [    INFO] - [INFO] checkpoint saved to: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:05:22,997 -        meta learning: [    INFO] - [INFO] tensorboard dir set to: ./runs/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:05:22,997 -        meta learning: [    INFO] - [ARGS]: Namespace(policy='GruPolicy', algo='PGPE', task='SeqTask', seq_length=20, latency=24, num_cls=5, feature_dims=14, sigma=0.1, batch_size=512, hidden_dims=[128], pop_size=256, center_lr=0.01, init_std=0.04, decay_std=0.999, limit_std=0.001, std_lr=0.07, terminate_when_unhealthy=False, max_iters=12000, num_tasks=1, seed=42, num_tests=128, eval_epoch=100, eval=False, eval_with_injury=False, resume='', save=False, repeat=20, root_dir='/data/anonymous/meta', tensorboard_dir='./runs', suffix='', output_dir='/data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522', summary_writer=<torch.utils.tensorboard.writer.SummaryWriter object at 0x7fa1c877bdf0>, tb_prefix='PGPE/SeqTask/GruPolicy')
2023-07-07 00:05:26,038 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:05:26,038 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:05:26,104 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:05:32,327 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=4.137e+05
2023-07-07 00:05:35,235 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=8.233e+05
2023-07-07 00:05:38,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.233e+06
2023-07-07 00:05:41,035 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=1.642e+06
2023-07-07 00:05:43,921 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=2.052e+06
2023-07-07 00:05:46,808 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=2.462e+06
2023-07-07 00:05:49,697 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=2.871e+06
2023-07-07 00:05:52,583 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=3.281e+06
2023-07-07 00:05:55,460 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=3.690e+06
2023-07-07 00:05:58,355 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=4.100e+06
2023-07-07 00:06:01,231 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=4.510e+06
2023-07-07 00:06:04,109 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=4.919e+06
2023-07-07 00:06:07,004 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=5.329e+06
2023-07-07 00:06:09,905 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=5.738e+06
2023-07-07 00:06:12,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=6.148e+06
2023-07-07 00:06:15,711 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=6.558e+06
2023-07-07 00:06:18,604 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=6.967e+06
2023-07-07 00:06:21,501 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=7.377e+06
2023-07-07 00:06:24,384 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=7.786e+06
2023-07-07 00:06:27,261 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=8.196e+06
2023-07-07 00:06:30,143 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=8.606e+06
2023-07-07 00:06:33,029 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=9.015e+06
2023-07-07 00:06:35,917 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=9.425e+06
2023-07-07 00:06:38,810 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=9.834e+06
2023-07-07 00:06:41,712 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.024e+07
2023-07-07 00:06:44,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.065e+07
2023-07-07 00:06:47,524 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.106e+07
2023-07-07 00:06:50,418 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.147e+07
2023-07-07 00:06:53,307 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.188e+07
2023-07-07 00:06:56,183 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 00:06:59,059 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.270e+07
2023-07-07 00:07:01,938 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.311e+07
2023-07-07 00:07:04,813 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 00:07:07,707 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 00:07:10,606 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=1.434e+07
2023-07-07 00:07:13,484 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 00:07:16,363 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=1.516e+07
2023-07-07 00:07:19,236 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 00:07:22,117 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 00:07:25,010 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 00:07:27,912 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=1.680e+07
2023-07-07 00:07:30,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 00:07:33,720 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=1.762e+07
2023-07-07 00:07:36,618 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 00:07:39,517 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 00:07:42,414 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 00:07:45,306 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=1.926e+07
2023-07-07 00:07:48,206 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=1.966e+07
2023-07-07 00:07:51,077 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=2.007e+07
2023-07-07 00:07:53,954 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=2.048e+07
2023-07-07 00:07:56,825 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=2.089e+07
2023-07-07 00:07:59,709 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=2.130e+07
2023-07-07 00:08:02,590 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=2.171e+07
2023-07-07 00:08:05,470 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 00:08:08,349 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=2.253e+07
2023-07-07 00:08:11,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=2.294e+07
2023-07-07 00:08:14,129 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 00:08:17,027 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 00:08:19,906 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=2.417e+07
2023-07-07 00:08:22,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 00:08:25,700 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=2.499e+07
2023-07-07 00:08:28,603 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 00:08:31,507 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 00:08:34,412 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 00:08:37,308 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 00:08:40,203 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 00:08:43,088 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=2.745e+07
2023-07-07 00:08:45,969 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 00:08:48,848 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 00:08:51,732 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 00:08:54,614 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=2.909e+07
2023-07-07 00:08:57,491 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 00:09:00,373 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=2.990e+07
2023-07-07 00:09:03,280 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=3.031e+07
2023-07-07 00:09:06,195 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=3.072e+07
2023-07-07 00:09:09,107 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=3.113e+07
2023-07-07 00:09:12,011 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=3.154e+07
2023-07-07 00:09:14,914 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 00:09:17,801 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=3.236e+07
2023-07-07 00:09:20,682 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=3.277e+07
2023-07-07 00:09:23,564 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 00:09:26,444 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=3.359e+07
2023-07-07 00:09:29,329 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=3.400e+07
2023-07-07 00:09:32,228 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 00:09:35,120 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=3.482e+07
2023-07-07 00:09:38,023 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 00:09:40,917 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 00:09:43,797 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8800, best=0.71, avg=0.69, std=0.01, steps=3.605e+07
2023-07-07 00:09:46,680 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8900, best=0.78, avg=0.76, std=0.01, steps=3.646e+07
2023-07-07 00:09:49,567 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9000, best=0.81, avg=0.80, std=0.01, steps=3.687e+07
2023-07-07 00:09:52,457 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=3.728e+07
2023-07-07 00:09:55,359 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9200, best=0.88, avg=0.86, std=0.01, steps=3.769e+07
2023-07-07 00:09:58,264 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9300, best=0.89, avg=0.87, std=0.01, steps=3.810e+07
2023-07-07 00:10:01,171 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9400, best=0.90, avg=0.89, std=0.00, steps=3.851e+07
2023-07-07 00:10:04,064 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9500, best=0.90, avg=0.90, std=0.00, steps=3.892e+07
2023-07-07 00:10:06,938 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9600, best=0.92, avg=0.91, std=0.00, steps=3.933e+07
2023-07-07 00:10:09,821 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9700, best=0.93, avg=0.92, std=0.00, steps=3.974e+07
2023-07-07 00:10:12,714 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9800, best=0.94, avg=0.93, std=0.00, steps=4.014e+07
2023-07-07 00:10:15,618 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9900, best=0.94, avg=0.94, std=0.00, steps=4.055e+07
2023-07-07 00:10:18,533 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10000, best=0.95, avg=0.94, std=0.00, steps=4.096e+07
2023-07-07 00:10:21,437 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10100, best=0.95, avg=0.94, std=0.00, steps=4.137e+07
2023-07-07 00:10:24,324 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10200, best=0.95, avg=0.94, std=0.00, steps=4.178e+07
2023-07-07 00:10:27,215 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10300, best=0.95, avg=0.94, std=0.00, steps=4.219e+07
2023-07-07 00:10:30,102 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10400, best=0.95, avg=0.94, std=0.00, steps=4.260e+07
2023-07-07 00:10:32,989 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10500, best=0.95, avg=0.94, std=0.00, steps=4.301e+07
2023-07-07 00:10:35,872 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10600, best=0.95, avg=0.95, std=0.00, steps=4.342e+07
2023-07-07 00:10:38,756 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10700, best=0.95, avg=0.95, std=0.00, steps=4.383e+07
2023-07-07 00:10:41,637 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10800, best=0.95, avg=0.95, std=0.00, steps=4.424e+07
2023-07-07 00:10:44,518 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10900, best=0.97, avg=0.96, std=0.00, steps=4.465e+07
2023-07-07 00:10:47,403 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11000, best=0.98, avg=0.97, std=0.00, steps=4.506e+07
2023-07-07 00:10:50,284 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11100, best=0.98, avg=0.98, std=0.00, steps=4.547e+07
2023-07-07 00:10:53,163 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11200, best=0.99, avg=0.99, std=0.00, steps=4.588e+07
2023-07-07 00:10:56,037 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11300, best=0.99, avg=0.99, std=0.00, steps=4.629e+07
2023-07-07 00:10:58,913 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11400, best=1.00, avg=1.00, std=0.00, steps=4.670e+07
2023-07-07 00:11:01,816 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11500, best=1.00, avg=1.00, std=0.00, steps=4.711e+07
2023-07-07 00:11:04,701 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11600, best=1.00, avg=1.00, std=0.00, steps=4.752e+07
2023-07-07 00:11:07,578 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11700, best=1.00, avg=1.00, std=0.00, steps=4.793e+07
2023-07-07 00:11:10,475 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11800, best=1.00, avg=1.00, std=0.00, steps=4.834e+07
2023-07-07 00:11:13,364 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11900, best=1.00, avg=1.00, std=0.00, steps=4.875e+07
2023-07-07 00:11:16,227 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11999, best=1.00, avg=1.00, std=0.00, steps=4.915e+07
2023-07-07 00:11:16,228 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:11:16,256 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:11:16,256 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:11:16,288 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:11:22,055 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=6.205e+05
2023-07-07 00:11:26,240 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.235e+06
2023-07-07 00:11:30,426 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.849e+06
2023-07-07 00:11:34,609 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=2.464e+06
2023-07-07 00:11:38,795 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=3.078e+06
2023-07-07 00:11:42,984 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=3.693e+06
2023-07-07 00:11:47,165 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=4.307e+06
2023-07-07 00:11:51,352 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=4.921e+06
2023-07-07 00:11:55,541 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=5.536e+06
2023-07-07 00:11:59,733 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=6.150e+06
2023-07-07 00:12:03,925 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=6.765e+06
2023-07-07 00:12:08,141 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=7.379e+06
2023-07-07 00:12:12,353 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=7.993e+06
2023-07-07 00:12:16,569 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=8.608e+06
2023-07-07 00:12:20,775 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=9.222e+06
2023-07-07 00:12:24,971 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=9.837e+06
2023-07-07 00:12:29,156 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.045e+07
2023-07-07 00:12:33,329 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 00:12:37,503 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.168e+07
2023-07-07 00:12:41,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 00:12:45,849 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.291e+07
2023-07-07 00:12:50,015 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 00:12:54,203 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.414e+07
2023-07-07 00:12:58,369 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 00:13:02,563 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 00:13:06,768 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 00:13:10,940 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.659e+07
2023-07-07 00:13:15,112 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 00:13:19,283 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.782e+07
2023-07-07 00:13:23,475 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 00:13:27,647 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.905e+07
2023-07-07 00:13:31,848 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 00:13:36,057 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.028e+07
2023-07-07 00:13:40,241 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 00:13:44,413 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 00:13:48,584 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 00:13:52,756 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=2.274e+07
2023-07-07 00:13:56,926 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 00:14:01,130 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=2.397e+07
2023-07-07 00:14:05,334 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 00:14:09,541 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=2.520e+07
2023-07-07 00:14:13,715 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 00:14:17,889 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=2.643e+07
2023-07-07 00:14:22,067 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 00:14:26,228 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=2.765e+07
2023-07-07 00:14:30,398 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 00:14:34,585 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=2.888e+07
2023-07-07 00:14:38,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 00:14:42,978 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=3.011e+07
2023-07-07 00:14:47,176 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 00:14:51,383 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=3.134e+07
2023-07-07 00:14:55,575 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 00:14:59,770 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=3.257e+07
2023-07-07 00:15:03,964 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 00:15:08,136 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 00:15:12,356 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 00:15:16,575 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=3.503e+07
2023-07-07 00:15:20,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 00:15:24,955 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=3.626e+07
2023-07-07 00:15:29,126 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 00:15:33,321 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=3.748e+07
2023-07-07 00:15:37,523 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=3.810e+07
2023-07-07 00:15:41,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=3.871e+07
2023-07-07 00:15:45,852 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 00:15:50,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=3.994e+07
2023-07-07 00:15:54,170 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 00:15:58,348 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=4.117e+07
2023-07-07 00:16:02,542 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 00:16:06,744 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=4.240e+07
2023-07-07 00:16:10,935 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=4.301e+07
2023-07-07 00:16:15,121 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=4.363e+07
2023-07-07 00:16:19,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7200, best=0.66, avg=0.64, std=0.00, steps=4.424e+07
2023-07-07 00:16:23,453 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7300, best=0.72, avg=0.70, std=0.01, steps=4.486e+07
2023-07-07 00:16:27,617 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=4.547e+07
2023-07-07 00:16:31,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7500, best=0.74, avg=0.73, std=0.01, steps=4.609e+07
2023-07-07 00:16:35,990 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7600, best=0.74, avg=0.73, std=0.01, steps=4.670e+07
2023-07-07 00:16:40,177 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7700, best=0.75, avg=0.74, std=0.01, steps=4.731e+07
2023-07-07 00:16:44,362 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7800, best=0.77, avg=0.75, std=0.01, steps=4.793e+07
2023-07-07 00:16:48,569 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7900, best=0.78, avg=0.76, std=0.01, steps=4.854e+07
2023-07-07 00:16:52,756 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8000, best=0.79, avg=0.77, std=0.01, steps=4.916e+07
2023-07-07 00:16:56,927 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8100, best=0.79, avg=0.77, std=0.01, steps=4.977e+07
2023-07-07 00:17:01,092 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8200, best=0.79, avg=0.78, std=0.01, steps=5.039e+07
2023-07-07 00:17:05,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8300, best=0.80, avg=0.79, std=0.01, steps=5.100e+07
2023-07-07 00:17:09,461 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8400, best=0.81, avg=0.79, std=0.01, steps=5.162e+07
2023-07-07 00:17:13,630 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8500, best=0.82, avg=0.80, std=0.01, steps=5.223e+07
2023-07-07 00:17:17,857 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8600, best=0.82, avg=0.81, std=0.01, steps=5.284e+07
2023-07-07 00:17:22,082 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8700, best=0.83, avg=0.81, std=0.01, steps=5.346e+07
2023-07-07 00:17:26,295 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8800, best=0.83, avg=0.81, std=0.00, steps=5.407e+07
2023-07-07 00:17:30,471 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8900, best=0.83, avg=0.81, std=0.01, steps=5.469e+07
2023-07-07 00:17:34,644 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9000, best=0.84, avg=0.82, std=0.01, steps=5.530e+07
2023-07-07 00:17:38,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=5.592e+07
2023-07-07 00:17:42,994 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9200, best=0.85, avg=0.83, std=0.01, steps=5.653e+07
2023-07-07 00:17:47,170 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9300, best=0.85, avg=0.84, std=0.00, steps=5.715e+07
2023-07-07 00:17:51,391 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9400, best=0.86, avg=0.84, std=0.01, steps=5.776e+07
2023-07-07 00:17:55,599 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9500, best=0.85, avg=0.84, std=0.00, steps=5.837e+07
2023-07-07 00:17:59,786 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9600, best=0.86, avg=0.85, std=0.00, steps=5.899e+07
2023-07-07 00:18:03,969 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9700, best=0.86, avg=0.85, std=0.00, steps=5.960e+07
2023-07-07 00:18:08,158 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9800, best=0.87, avg=0.85, std=0.00, steps=6.022e+07
2023-07-07 00:18:12,367 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9900, best=0.88, avg=0.86, std=0.00, steps=6.083e+07
2023-07-07 00:18:16,591 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10000, best=0.88, avg=0.86, std=0.00, steps=6.145e+07
2023-07-07 00:18:20,771 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10100, best=0.88, avg=0.87, std=0.00, steps=6.206e+07
2023-07-07 00:18:24,949 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10200, best=0.89, avg=0.88, std=0.00, steps=6.267e+07
2023-07-07 00:18:29,128 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10300, best=0.89, avg=0.88, std=0.00, steps=6.329e+07
2023-07-07 00:18:33,305 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10400, best=0.90, avg=0.89, std=0.00, steps=6.390e+07
2023-07-07 00:18:37,482 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10500, best=0.90, avg=0.88, std=0.00, steps=6.452e+07
2023-07-07 00:18:41,660 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10600, best=0.90, avg=0.89, std=0.00, steps=6.513e+07
2023-07-07 00:18:45,845 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10700, best=0.90, avg=0.89, std=0.00, steps=6.575e+07
2023-07-07 00:18:50,013 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10800, best=0.90, avg=0.89, std=0.00, steps=6.636e+07
2023-07-07 00:18:54,186 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10900, best=0.90, avg=0.89, std=0.00, steps=6.698e+07
2023-07-07 00:18:58,358 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11000, best=0.91, avg=0.90, std=0.00, steps=6.759e+07
2023-07-07 00:19:02,545 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11100, best=0.91, avg=0.90, std=0.00, steps=6.820e+07
2023-07-07 00:19:06,727 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11200, best=0.91, avg=0.90, std=0.00, steps=6.882e+07
2023-07-07 00:19:10,906 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11300, best=0.91, avg=0.90, std=0.00, steps=6.943e+07
2023-07-07 00:19:15,086 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11400, best=0.91, avg=0.90, std=0.00, steps=7.005e+07
2023-07-07 00:19:19,261 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11500, best=0.91, avg=0.90, std=0.00, steps=7.066e+07
2023-07-07 00:19:23,436 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11600, best=0.92, avg=0.90, std=0.00, steps=7.128e+07
2023-07-07 00:19:27,607 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11700, best=0.92, avg=0.91, std=0.00, steps=7.189e+07
2023-07-07 00:19:31,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11800, best=0.92, avg=0.91, std=0.00, steps=7.251e+07
2023-07-07 00:19:35,966 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11900, best=0.92, avg=0.91, std=0.00, steps=7.312e+07
2023-07-07 00:19:40,106 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11999, best=0.92, avg=0.91, std=0.00, steps=7.373e+07
2023-07-07 00:19:40,107 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:19:40,131 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:19:40,132 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:19:40,162 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:19:47,191 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 00:19:52,714 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 00:19:58,187 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 00:20:03,710 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 00:20:09,213 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 00:20:14,697 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 00:20:20,185 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 00:20:25,699 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 00:20:31,180 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 00:20:36,664 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 00:20:42,164 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=9.019e+06
2023-07-07 00:20:47,679 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 00:20:53,153 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 00:20:58,625 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 00:21:04,113 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 00:21:09,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 00:21:15,050 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 00:21:20,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 00:21:26,043 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 00:21:31,502 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 00:21:36,954 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 00:21:42,403 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 00:21:47,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 00:21:53,346 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 00:21:58,849 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 00:22:04,310 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 00:22:09,776 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 00:22:15,274 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 00:22:20,789 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 00:22:26,297 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 00:22:31,791 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 00:22:37,257 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 00:22:42,720 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 00:22:48,187 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 00:22:53,636 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 00:22:59,090 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 00:23:04,550 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 00:23:10,016 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 00:23:15,472 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 00:23:20,937 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 00:23:26,406 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 00:23:31,876 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 00:23:37,368 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 00:23:42,851 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 00:23:48,326 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 00:23:53,795 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 00:23:59,250 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 00:24:04,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 00:24:10,187 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 00:24:15,645 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 00:24:21,150 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 00:24:26,620 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 00:24:32,129 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 00:24:37,621 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 00:24:43,132 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 00:24:48,627 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 00:24:54,094 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 00:24:59,559 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 00:25:05,024 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 00:25:10,499 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 00:25:15,981 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 00:25:21,456 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 00:25:26,934 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 00:25:32,404 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 00:25:37,864 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 00:25:43,330 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 00:25:48,798 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 00:25:54,263 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 00:25:59,721 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 00:26:05,207 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 00:26:10,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 00:26:16,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 00:26:21,740 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7300, best=0.71, avg=0.69, std=0.01, steps=5.981e+07
2023-07-07 00:26:27,250 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=6.063e+07
2023-07-07 00:26:32,752 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7500, best=0.73, avg=0.71, std=0.01, steps=6.145e+07
2023-07-07 00:26:38,269 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7600, best=0.73, avg=0.72, std=0.01, steps=6.227e+07
2023-07-07 00:26:43,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7700, best=0.73, avg=0.72, std=0.01, steps=6.309e+07
2023-07-07 00:26:49,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7800, best=0.74, avg=0.73, std=0.01, steps=6.391e+07
2023-07-07 00:26:54,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7900, best=0.75, avg=0.73, std=0.01, steps=6.472e+07
2023-07-07 00:27:00,179 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8000, best=0.75, avg=0.74, std=0.01, steps=6.554e+07
2023-07-07 00:27:05,648 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8100, best=0.76, avg=0.75, std=0.01, steps=6.636e+07
2023-07-07 00:27:11,137 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8200, best=0.77, avg=0.76, std=0.00, steps=6.718e+07
2023-07-07 00:27:16,630 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8300, best=0.78, avg=0.77, std=0.01, steps=6.800e+07
2023-07-07 00:27:22,146 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8400, best=0.79, avg=0.78, std=0.01, steps=6.882e+07
2023-07-07 00:27:27,662 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8500, best=0.80, avg=0.78, std=0.01, steps=6.964e+07
2023-07-07 00:27:33,191 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8600, best=0.81, avg=0.79, std=0.01, steps=7.046e+07
2023-07-07 00:27:38,688 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8700, best=0.80, avg=0.79, std=0.01, steps=7.128e+07
2023-07-07 00:27:44,196 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8800, best=0.81, avg=0.80, std=0.01, steps=7.210e+07
2023-07-07 00:27:49,705 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8900, best=0.82, avg=0.80, std=0.01, steps=7.292e+07
2023-07-07 00:27:55,181 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9000, best=0.82, avg=0.80, std=0.01, steps=7.374e+07
2023-07-07 00:28:00,641 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9100, best=0.82, avg=0.81, std=0.01, steps=7.456e+07
2023-07-07 00:28:06,104 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9200, best=0.83, avg=0.81, std=0.01, steps=7.537e+07
2023-07-07 00:28:11,570 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9300, best=0.83, avg=0.81, std=0.01, steps=7.619e+07
2023-07-07 00:28:17,037 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9400, best=0.83, avg=0.82, std=0.01, steps=7.701e+07
2023-07-07 00:28:22,546 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9500, best=0.84, avg=0.82, std=0.01, steps=7.783e+07
2023-07-07 00:28:28,063 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9600, best=0.84, avg=0.83, std=0.01, steps=7.865e+07
2023-07-07 00:28:33,582 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9700, best=0.84, avg=0.83, std=0.00, steps=7.947e+07
2023-07-07 00:28:39,103 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9800, best=0.84, avg=0.83, std=0.00, steps=8.029e+07
2023-07-07 00:28:44,608 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9900, best=0.85, avg=0.83, std=0.00, steps=8.111e+07
2023-07-07 00:28:50,116 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10000, best=0.85, avg=0.83, std=0.00, steps=8.193e+07
2023-07-07 00:28:55,612 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10100, best=0.85, avg=0.84, std=0.01, steps=8.275e+07
2023-07-07 00:29:01,073 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10200, best=0.85, avg=0.84, std=0.01, steps=8.357e+07
2023-07-07 00:29:06,537 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10300, best=0.85, avg=0.84, std=0.01, steps=8.439e+07
2023-07-07 00:29:12,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10400, best=0.85, avg=0.84, std=0.00, steps=8.520e+07
2023-07-07 00:29:17,488 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10500, best=0.85, avg=0.84, std=0.00, steps=8.602e+07
2023-07-07 00:29:22,959 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10600, best=0.86, avg=0.84, std=0.01, steps=8.684e+07
2023-07-07 00:29:28,444 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10700, best=0.86, avg=0.85, std=0.00, steps=8.766e+07
2023-07-07 00:29:33,953 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10800, best=0.86, avg=0.85, std=0.01, steps=8.848e+07
2023-07-07 00:29:39,437 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10900, best=0.86, avg=0.85, std=0.00, steps=8.930e+07
2023-07-07 00:29:44,886 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11000, best=0.86, avg=0.85, std=0.00, steps=9.012e+07
2023-07-07 00:29:50,342 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11100, best=0.86, avg=0.85, std=0.00, steps=9.094e+07
2023-07-07 00:29:55,812 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11200, best=0.87, avg=0.85, std=0.00, steps=9.176e+07
2023-07-07 00:30:01,289 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11300, best=0.86, avg=0.86, std=0.00, steps=9.258e+07
2023-07-07 00:30:06,764 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11400, best=0.87, avg=0.86, std=0.00, steps=9.340e+07
2023-07-07 00:30:12,251 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11500, best=0.87, avg=0.86, std=0.00, steps=9.422e+07
2023-07-07 00:30:17,776 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11600, best=0.87, avg=0.86, std=0.00, steps=9.504e+07
2023-07-07 00:30:23,313 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11700, best=0.87, avg=0.86, std=0.00, steps=9.585e+07
2023-07-07 00:30:28,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11800, best=0.87, avg=0.86, std=0.00, steps=9.667e+07
2023-07-07 00:30:34,339 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11900, best=0.87, avg=0.86, std=0.00, steps=9.749e+07
2023-07-07 00:30:39,798 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11999, best=0.87, avg=0.86, std=0.00, steps=9.830e+07
2023-07-07 00:30:39,799 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:30:39,824 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:30:39,824 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:30:39,855 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:30:49,500 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 00:30:57,562 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 00:31:05,630 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 00:31:13,689 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 00:31:21,750 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 00:31:29,811 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 00:31:37,894 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 00:31:46,015 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 00:31:54,099 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 00:32:02,155 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 00:32:10,206 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 00:32:18,259 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 00:32:26,317 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.599e+07
2023-07-07 00:32:34,374 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 00:32:42,406 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 00:32:50,444 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 00:32:58,494 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 00:33:06,550 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 00:33:14,610 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 00:33:22,710 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 00:33:30,823 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 00:33:38,884 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=2.705e+07
2023-07-07 00:33:46,951 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 00:33:54,997 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 00:34:03,044 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 00:34:11,090 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 00:34:19,129 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 00:34:27,163 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 00:34:35,208 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 00:34:43,259 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 00:34:51,364 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 00:34:59,454 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 00:35:07,497 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 00:35:15,538 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 00:35:23,631 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 00:35:31,765 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 00:35:39,885 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 00:35:47,951 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 00:35:55,995 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 00:36:04,047 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 00:36:12,098 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 00:36:20,194 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 00:36:28,312 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 00:36:36,393 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 00:36:44,498 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 00:36:52,606 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 00:37:00,662 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 00:37:08,718 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 00:37:16,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 00:37:24,813 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 00:37:32,888 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 00:37:40,953 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 00:37:49,075 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=6.514e+07
2023-07-07 00:37:57,181 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 00:38:05,283 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 00:38:13,355 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 00:38:21,405 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 00:38:29,466 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 00:38:37,610 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 00:38:45,672 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 00:38:53,723 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 00:39:01,769 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 00:39:09,820 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 00:39:17,869 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 00:39:25,913 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 00:39:33,970 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 00:39:42,085 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 00:39:50,178 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 00:39:58,260 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 00:40:06,316 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 00:40:14,396 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 00:40:22,528 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 00:40:30,603 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 00:40:38,645 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 00:40:46,698 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 00:40:54,764 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 00:41:02,831 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 00:41:10,895 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 00:41:18,963 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 00:41:27,037 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 00:41:35,124 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 00:41:43,189 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 00:41:51,249 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 00:41:59,310 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 00:42:07,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 00:42:15,433 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=1.057e+08
2023-07-07 00:42:23,515 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.069e+08
2023-07-07 00:42:31,636 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 00:42:39,744 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=1.094e+08
2023-07-07 00:42:47,813 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.106e+08
2023-07-07 00:42:55,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 00:43:03,946 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 00:43:11,980 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=1.143e+08
2023-07-07 00:43:20,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=1.155e+08
2023-07-07 00:43:28,062 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=1.167e+08
2023-07-07 00:43:36,144 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 00:43:44,196 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=1.192e+08
2023-07-07 00:43:52,260 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9800, best=0.53, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 00:44:00,319 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=1.217e+08
2023-07-07 00:44:08,377 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 00:44:16,449 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 00:44:24,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.253e+08
2023-07-07 00:44:32,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=1.266e+08
2023-07-07 00:44:40,638 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 00:44:48,767 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.290e+08
2023-07-07 00:44:56,892 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=1.303e+08
2023-07-07 00:45:05,014 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10700, best=0.65, avg=0.64, std=0.00, steps=1.315e+08
2023-07-07 00:45:13,142 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10800, best=0.65, avg=0.64, std=0.01, steps=1.327e+08
2023-07-07 00:45:21,251 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10900, best=0.64, avg=0.63, std=0.01, steps=1.340e+08
2023-07-07 00:45:29,358 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11000, best=0.66, avg=0.65, std=0.01, steps=1.352e+08
2023-07-07 00:45:37,442 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11100, best=0.67, avg=0.66, std=0.00, steps=1.364e+08
2023-07-07 00:45:45,571 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11200, best=0.68, avg=0.67, std=0.01, steps=1.376e+08
2023-07-07 00:45:53,697 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11300, best=0.68, avg=0.67, std=0.01, steps=1.389e+08
2023-07-07 00:46:01,830 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11400, best=0.68, avg=0.67, std=0.01, steps=1.401e+08
2023-07-07 00:46:09,959 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11500, best=0.69, avg=0.67, std=0.01, steps=1.413e+08
2023-07-07 00:46:18,088 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11600, best=0.69, avg=0.67, std=0.01, steps=1.426e+08
2023-07-07 00:46:26,212 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11700, best=0.69, avg=0.68, std=0.01, steps=1.438e+08
2023-07-07 00:46:34,335 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11800, best=0.69, avg=0.68, std=0.01, steps=1.450e+08
2023-07-07 00:46:42,466 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11900, best=0.70, avg=0.68, std=0.01, steps=1.462e+08
2023-07-07 00:46:50,435 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11999, best=0.71, avg=0.69, std=0.01, steps=1.475e+08
2023-07-07 00:46:50,435 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:46:50,468 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:46:50,469 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:46:50,501 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:46:57,458 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 00:47:02,940 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 00:47:08,432 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 00:47:13,941 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 00:47:19,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 00:47:24,948 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 00:47:30,469 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 00:47:35,985 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 00:47:41,488 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 00:47:46,967 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 00:47:52,439 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=9.019e+06
2023-07-07 00:47:57,929 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 00:48:03,399 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 00:48:08,857 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 00:48:14,319 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 00:48:19,794 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.312e+07
2023-07-07 00:48:25,261 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 00:48:30,741 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 00:48:36,244 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 00:48:41,770 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 00:48:47,256 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 00:48:52,757 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=1.803e+07
2023-07-07 00:48:58,245 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 00:49:03,719 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 00:49:09,184 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 00:49:14,669 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 00:49:20,149 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 00:49:25,621 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 00:49:31,092 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 00:49:36,599 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 00:49:42,122 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 00:49:47,613 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 00:49:53,086 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 00:49:58,581 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 00:50:04,057 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 00:50:09,539 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 00:50:15,017 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 00:50:20,485 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 00:50:25,987 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 00:50:31,503 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 00:50:37,014 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 00:50:42,500 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=3.441e+07
2023-07-07 00:50:47,960 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 00:50:53,408 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 00:50:58,883 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 00:51:04,351 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 00:51:09,853 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 00:51:15,327 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 00:51:20,801 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 00:51:26,326 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 00:51:31,786 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 00:51:37,278 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 00:51:42,744 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 00:51:48,199 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 00:51:53,658 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 00:51:59,125 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 00:52:04,587 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 00:52:10,052 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 00:52:15,512 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 00:52:20,983 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 00:52:26,460 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 00:52:31,936 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 00:52:37,409 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 00:52:42,915 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=5.244e+07
2023-07-07 00:52:48,428 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 00:52:53,910 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 00:52:59,368 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 00:53:04,852 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 00:53:10,333 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 00:53:15,792 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 00:53:21,251 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 00:53:26,723 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 00:53:32,245 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=5.981e+07
2023-07-07 00:53:37,757 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=6.063e+07
2023-07-07 00:53:43,244 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 00:53:48,715 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=6.227e+07
2023-07-07 00:53:54,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=6.309e+07
2023-07-07 00:53:59,640 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 00:54:05,098 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=6.472e+07
2023-07-07 00:54:10,557 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=6.554e+07
2023-07-07 00:54:16,015 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8100, best=0.68, avg=0.67, std=0.00, steps=6.636e+07
2023-07-07 00:54:21,473 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8200, best=0.71, avg=0.70, std=0.00, steps=6.718e+07
2023-07-07 00:54:26,934 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8300, best=0.73, avg=0.72, std=0.00, steps=6.800e+07
2023-07-07 00:54:32,393 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8400, best=0.75, avg=0.74, std=0.00, steps=6.882e+07
2023-07-07 00:54:37,857 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8500, best=0.76, avg=0.75, std=0.00, steps=6.964e+07
2023-07-07 00:54:43,360 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8600, best=0.77, avg=0.76, std=0.00, steps=7.046e+07
2023-07-07 00:54:48,835 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8700, best=0.77, avg=0.76, std=0.00, steps=7.128e+07
2023-07-07 00:54:54,310 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8800, best=0.78, avg=0.77, std=0.00, steps=7.210e+07
2023-07-07 00:54:59,789 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8900, best=0.79, avg=0.78, std=0.00, steps=7.292e+07
2023-07-07 00:55:05,269 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9000, best=0.80, avg=0.79, std=0.00, steps=7.374e+07
2023-07-07 00:55:10,745 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9100, best=0.81, avg=0.80, std=0.00, steps=7.456e+07
2023-07-07 00:55:16,228 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9200, best=0.81, avg=0.80, std=0.00, steps=7.537e+07
2023-07-07 00:55:21,709 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9300, best=0.82, avg=0.81, std=0.00, steps=7.619e+07
2023-07-07 00:55:27,176 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9400, best=0.83, avg=0.82, std=0.00, steps=7.701e+07
2023-07-07 00:55:32,672 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9500, best=0.83, avg=0.82, std=0.00, steps=7.783e+07
2023-07-07 00:55:38,159 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9600, best=0.84, avg=0.83, std=0.00, steps=7.865e+07
2023-07-07 00:55:43,626 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9700, best=0.85, avg=0.84, std=0.00, steps=7.947e+07
2023-07-07 00:55:49,127 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9800, best=0.85, avg=0.84, std=0.00, steps=8.029e+07
2023-07-07 00:55:54,641 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9900, best=0.85, avg=0.85, std=0.00, steps=8.111e+07
2023-07-07 00:56:00,127 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10000, best=0.86, avg=0.85, std=0.00, steps=8.193e+07
2023-07-07 00:56:05,590 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10100, best=0.86, avg=0.86, std=0.00, steps=8.275e+07
2023-07-07 00:56:11,086 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10200, best=0.87, avg=0.86, std=0.00, steps=8.357e+07
2023-07-07 00:56:16,561 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10300, best=0.87, avg=0.86, std=0.00, steps=8.439e+07
2023-07-07 00:56:22,012 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10400, best=0.88, avg=0.87, std=0.00, steps=8.520e+07
2023-07-07 00:56:27,510 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10500, best=0.88, avg=0.87, std=0.00, steps=8.602e+07
2023-07-07 00:56:32,992 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10600, best=0.88, avg=0.87, std=0.00, steps=8.684e+07
2023-07-07 00:56:38,510 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10700, best=0.89, avg=0.88, std=0.00, steps=8.766e+07
2023-07-07 00:56:44,048 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10800, best=0.89, avg=0.88, std=0.00, steps=8.848e+07
2023-07-07 00:56:49,569 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10900, best=0.89, avg=0.88, std=0.00, steps=8.930e+07
2023-07-07 00:56:55,028 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11000, best=0.89, avg=0.88, std=0.00, steps=9.012e+07
2023-07-07 00:57:00,537 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11100, best=0.89, avg=0.88, std=0.00, steps=9.094e+07
2023-07-07 00:57:06,051 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11200, best=0.89, avg=0.89, std=0.00, steps=9.176e+07
2023-07-07 00:57:11,522 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11300, best=0.90, avg=0.89, std=0.00, steps=9.258e+07
2023-07-07 00:57:17,011 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11400, best=0.89, avg=0.89, std=0.00, steps=9.340e+07
2023-07-07 00:57:22,465 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11500, best=0.90, avg=0.89, std=0.00, steps=9.422e+07
2023-07-07 00:57:27,926 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11600, best=0.90, avg=0.89, std=0.00, steps=9.504e+07
2023-07-07 00:57:33,397 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11700, best=0.90, avg=0.89, std=0.00, steps=9.585e+07
2023-07-07 00:57:38,898 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11800, best=0.90, avg=0.89, std=0.00, steps=9.667e+07
2023-07-07 00:57:44,377 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11900, best=0.90, avg=0.89, std=0.00, steps=9.749e+07
2023-07-07 00:57:49,789 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11999, best=0.90, avg=0.89, std=0.00, steps=9.830e+07
2023-07-07 00:57:49,789 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 00:57:49,814 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 00:57:49,814 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 00:57:49,845 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 00:57:58,134 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.034e+06
2023-07-07 00:58:04,931 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=2.058e+06
2023-07-07 00:58:11,724 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.082e+06
2023-07-07 00:58:18,482 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.106e+06
2023-07-07 00:58:25,240 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=5.130e+06
2023-07-07 00:58:32,047 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=6.154e+06
2023-07-07 00:58:38,844 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=7.178e+06
2023-07-07 00:58:45,593 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=8.202e+06
2023-07-07 00:58:52,338 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=9.226e+06
2023-07-07 00:58:59,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.025e+07
2023-07-07 00:59:05,841 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.127e+07
2023-07-07 00:59:12,588 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 00:59:19,337 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.332e+07
2023-07-07 00:59:26,109 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.435e+07
2023-07-07 00:59:32,902 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 00:59:39,707 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.639e+07
2023-07-07 00:59:46,504 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=1.742e+07
2023-07-07 00:59:53,349 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 01:00:00,114 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.947e+07
2023-07-07 01:00:06,854 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 01:00:13,617 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 01:00:20,381 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=2.254e+07
2023-07-07 01:00:27,142 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.356e+07
2023-07-07 01:00:33,889 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 01:00:40,673 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=2.561e+07
2023-07-07 01:00:47,469 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 01:00:54,266 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.766e+07
2023-07-07 01:01:01,049 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 01:01:07,805 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=2.971e+07
2023-07-07 01:01:14,600 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 01:01:21,373 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=3.175e+07
2023-07-07 01:01:28,144 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 01:01:34,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 01:01:41,709 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=3.483e+07
2023-07-07 01:01:48,525 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=3.585e+07
2023-07-07 01:01:55,358 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 01:02:02,248 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.790e+07
2023-07-07 01:02:09,069 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=3.892e+07
2023-07-07 01:02:15,831 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=3.995e+07
2023-07-07 01:02:22,630 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 01:02:29,391 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=4.199e+07
2023-07-07 01:02:36,158 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=4.302e+07
2023-07-07 01:02:42,923 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=4.404e+07
2023-07-07 01:02:49,664 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=4.507e+07
2023-07-07 01:02:56,410 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=4.609e+07
2023-07-07 01:03:03,155 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=4.711e+07
2023-07-07 01:03:09,971 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=4.814e+07
2023-07-07 01:03:16,713 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 01:03:23,448 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=5.019e+07
2023-07-07 01:03:30,231 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=5.121e+07
2023-07-07 01:03:37,034 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=5.223e+07
2023-07-07 01:03:43,806 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 01:03:50,559 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=5.428e+07
2023-07-07 01:03:57,293 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 01:04:04,020 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=5.633e+07
2023-07-07 01:04:10,746 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 01:04:17,499 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=5.838e+07
2023-07-07 01:04:24,264 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=5.940e+07
2023-07-07 01:04:31,034 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=6.043e+07
2023-07-07 01:04:37,781 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 01:04:44,534 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=6.247e+07
2023-07-07 01:04:51,282 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=6.350e+07
2023-07-07 01:04:58,038 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=6.452e+07
2023-07-07 01:05:04,801 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=6.555e+07
2023-07-07 01:05:11,602 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=6.657e+07
2023-07-07 01:05:18,415 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=6.759e+07
2023-07-07 01:05:25,221 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=6.862e+07
2023-07-07 01:05:32,000 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=6.964e+07
2023-07-07 01:05:38,742 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=7.067e+07
2023-07-07 01:05:45,487 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=7.169e+07
2023-07-07 01:05:52,221 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=7.271e+07
2023-07-07 01:05:58,953 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 01:06:05,700 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=7.476e+07
2023-07-07 01:06:12,438 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=7.579e+07
2023-07-07 01:06:19,172 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=7.681e+07
2023-07-07 01:06:25,921 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=7.783e+07
2023-07-07 01:06:32,645 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=7.886e+07
2023-07-07 01:06:39,394 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7800, best=0.65, avg=0.64, std=0.00, steps=7.988e+07
2023-07-07 01:06:46,159 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7900, best=0.68, avg=0.67, std=0.00, steps=8.091e+07
2023-07-07 01:06:52,892 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8000, best=0.70, avg=0.69, std=0.00, steps=8.193e+07
2023-07-07 01:06:59,623 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8100, best=0.71, avg=0.70, std=0.00, steps=8.295e+07
2023-07-07 01:07:06,353 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8200, best=0.71, avg=0.70, std=0.00, steps=8.398e+07
2023-07-07 01:07:13,095 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8300, best=0.72, avg=0.71, std=0.00, steps=8.500e+07
2023-07-07 01:07:19,848 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8400, best=0.73, avg=0.71, std=0.00, steps=8.603e+07
2023-07-07 01:07:26,591 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8500, best=0.73, avg=0.72, std=0.00, steps=8.705e+07
2023-07-07 01:07:33,365 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8600, best=0.73, avg=0.72, std=0.00, steps=8.807e+07
2023-07-07 01:07:40,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8700, best=0.74, avg=0.73, std=0.00, steps=8.910e+07
2023-07-07 01:07:46,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8800, best=0.74, avg=0.73, std=0.00, steps=9.012e+07
2023-07-07 01:07:53,698 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8900, best=0.75, avg=0.74, std=0.00, steps=9.115e+07
2023-07-07 01:08:00,445 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9000, best=0.76, avg=0.75, std=0.00, steps=9.217e+07
2023-07-07 01:08:07,194 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9100, best=0.76, avg=0.75, std=0.00, steps=9.319e+07
2023-07-07 01:08:13,943 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9200, best=0.76, avg=0.75, std=0.00, steps=9.422e+07
2023-07-07 01:08:20,698 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9300, best=0.77, avg=0.76, std=0.00, steps=9.524e+07
2023-07-07 01:08:27,457 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9400, best=0.77, avg=0.76, std=0.00, steps=9.627e+07
2023-07-07 01:08:34,219 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9500, best=0.78, avg=0.77, std=0.00, steps=9.729e+07
2023-07-07 01:08:40,986 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9600, best=0.78, avg=0.77, std=0.00, steps=9.831e+07
2023-07-07 01:08:47,744 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9700, best=0.79, avg=0.77, std=0.00, steps=9.934e+07
2023-07-07 01:08:54,491 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9800, best=0.79, avg=0.78, std=0.00, steps=1.004e+08
2023-07-07 01:09:01,296 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9900, best=0.79, avg=0.78, std=0.00, steps=1.014e+08
2023-07-07 01:09:08,059 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10000, best=0.79, avg=0.78, std=0.00, steps=1.024e+08
2023-07-07 01:09:14,826 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10100, best=0.79, avg=0.79, std=0.00, steps=1.034e+08
2023-07-07 01:09:21,583 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10200, best=0.80, avg=0.79, std=0.00, steps=1.045e+08
2023-07-07 01:09:28,345 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10300, best=0.80, avg=0.79, std=0.00, steps=1.055e+08
2023-07-07 01:09:35,107 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10400, best=0.80, avg=0.79, std=0.00, steps=1.065e+08
2023-07-07 01:09:41,907 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10500, best=0.81, avg=0.79, std=0.00, steps=1.075e+08
2023-07-07 01:09:48,663 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10600, best=0.80, avg=0.80, std=0.00, steps=1.086e+08
2023-07-07 01:09:55,420 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10700, best=0.80, avg=0.80, std=0.00, steps=1.096e+08
2023-07-07 01:10:02,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10800, best=0.81, avg=0.80, std=0.00, steps=1.106e+08
2023-07-07 01:10:08,907 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10900, best=0.81, avg=0.80, std=0.00, steps=1.116e+08
2023-07-07 01:10:15,657 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11000, best=0.81, avg=0.80, std=0.00, steps=1.127e+08
2023-07-07 01:10:22,392 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11100, best=0.82, avg=0.81, std=0.00, steps=1.137e+08
2023-07-07 01:10:29,141 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11200, best=0.82, avg=0.81, std=0.00, steps=1.147e+08
2023-07-07 01:10:35,894 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11300, best=0.82, avg=0.81, std=0.00, steps=1.157e+08
2023-07-07 01:10:42,651 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11400, best=0.82, avg=0.81, std=0.00, steps=1.167e+08
2023-07-07 01:10:49,411 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11500, best=0.82, avg=0.81, std=0.00, steps=1.178e+08
2023-07-07 01:10:56,185 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11600, best=0.82, avg=0.81, std=0.00, steps=1.188e+08
2023-07-07 01:11:02,981 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11700, best=0.83, avg=0.82, std=0.00, steps=1.198e+08
2023-07-07 01:11:09,714 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11800, best=0.83, avg=0.82, std=0.00, steps=1.208e+08
2023-07-07 01:11:16,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11900, best=0.83, avg=0.82, std=0.00, steps=1.219e+08
2023-07-07 01:11:23,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11999, best=0.83, avg=0.82, std=0.00, steps=1.229e+08
2023-07-07 01:11:23,165 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 01:11:23,190 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 01:11:23,190 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 01:11:23,220 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 01:11:32,795 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 01:11:40,835 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 01:11:48,889 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 01:11:56,957 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 01:12:05,020 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 01:12:13,059 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 01:12:21,095 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 01:12:29,129 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 01:12:37,153 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 01:12:45,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 01:12:53,223 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 01:13:01,274 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 01:13:09,291 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.599e+07
2023-07-07 01:13:17,344 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 01:13:25,398 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 01:13:33,479 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.967e+07
2023-07-07 01:13:41,586 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 01:13:49,623 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 01:13:57,668 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 01:14:05,722 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 01:14:13,750 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 01:14:21,765 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=2.705e+07
2023-07-07 01:14:29,848 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 01:14:37,922 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 01:14:45,988 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 01:14:54,052 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 01:15:02,092 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 01:15:10,116 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 01:15:18,146 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 01:15:26,194 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 01:15:34,285 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 01:15:42,348 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 01:15:50,408 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 01:15:58,495 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 01:16:06,533 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 01:16:14,565 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 01:16:22,614 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 01:16:30,664 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 01:16:38,749 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 01:16:46,873 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 01:16:54,959 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 01:17:03,045 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=5.162e+07
2023-07-07 01:17:11,101 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 01:17:19,126 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 01:17:27,150 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 01:17:35,168 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 01:17:43,220 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 01:17:51,306 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 01:17:59,329 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 01:18:07,396 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 01:18:15,437 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 01:18:23,477 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 01:18:31,499 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=6.514e+07
2023-07-07 01:18:39,530 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 01:18:47,567 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 01:18:55,753 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 01:19:03,845 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 01:19:11,892 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 01:19:19,965 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 01:19:28,023 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 01:19:36,091 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 01:19:44,200 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 01:19:52,241 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 01:20:00,283 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=7.866e+07
2023-07-07 01:20:08,349 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 01:20:16,452 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 01:20:24,488 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 01:20:32,527 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 01:20:40,558 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 01:20:48,597 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 01:20:56,626 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 01:21:04,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 01:21:12,715 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 01:21:20,765 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 01:21:28,855 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 01:21:36,908 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 01:21:45,000 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 01:21:53,072 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 01:22:01,170 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 01:22:09,260 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 01:22:17,292 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 01:22:25,325 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 01:22:33,343 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 01:22:41,369 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 01:22:49,399 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 01:22:57,415 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8600, best=0.59, avg=0.58, std=0.00, steps=1.057e+08
2023-07-07 01:23:05,497 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8700, best=0.65, avg=0.64, std=0.00, steps=1.069e+08
2023-07-07 01:23:13,531 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8800, best=0.67, avg=0.66, std=0.00, steps=1.081e+08
2023-07-07 01:23:21,556 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8900, best=0.69, avg=0.68, std=0.00, steps=1.094e+08
2023-07-07 01:23:29,593 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9000, best=0.70, avg=0.69, std=0.00, steps=1.106e+08
2023-07-07 01:23:37,628 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9100, best=0.71, avg=0.70, std=0.00, steps=1.118e+08
2023-07-07 01:23:45,652 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9200, best=0.71, avg=0.70, std=0.00, steps=1.131e+08
2023-07-07 01:23:53,669 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9300, best=0.72, avg=0.70, std=0.00, steps=1.143e+08
2023-07-07 01:24:01,753 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9400, best=0.72, avg=0.71, std=0.00, steps=1.155e+08
2023-07-07 01:24:09,805 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9500, best=0.72, avg=0.71, std=0.00, steps=1.167e+08
2023-07-07 01:24:17,871 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9600, best=0.72, avg=0.71, std=0.00, steps=1.180e+08
2023-07-07 01:24:25,915 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9700, best=0.73, avg=0.72, std=0.00, steps=1.192e+08
2023-07-07 01:24:33,948 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9800, best=0.73, avg=0.72, std=0.00, steps=1.204e+08
2023-07-07 01:24:41,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9900, best=0.73, avg=0.72, std=0.00, steps=1.217e+08
2023-07-07 01:24:50,083 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10000, best=0.74, avg=0.73, std=0.00, steps=1.229e+08
2023-07-07 01:24:58,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10100, best=0.74, avg=0.73, std=0.00, steps=1.241e+08
2023-07-07 01:25:06,172 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10200, best=0.74, avg=0.73, std=0.00, steps=1.253e+08
2023-07-07 01:25:14,234 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10300, best=0.75, avg=0.73, std=0.00, steps=1.266e+08
2023-07-07 01:25:22,284 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10400, best=0.75, avg=0.74, std=0.00, steps=1.278e+08
2023-07-07 01:25:30,314 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10500, best=0.75, avg=0.74, std=0.00, steps=1.290e+08
2023-07-07 01:25:38,362 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10600, best=0.75, avg=0.74, std=0.00, steps=1.303e+08
2023-07-07 01:25:46,460 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10700, best=0.75, avg=0.74, std=0.00, steps=1.315e+08
2023-07-07 01:25:54,555 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10800, best=0.75, avg=0.74, std=0.00, steps=1.327e+08
2023-07-07 01:26:02,602 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10900, best=0.75, avg=0.74, std=0.00, steps=1.340e+08
2023-07-07 01:26:10,701 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11000, best=0.76, avg=0.75, std=0.00, steps=1.352e+08
2023-07-07 01:26:18,784 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11100, best=0.76, avg=0.75, std=0.00, steps=1.364e+08
2023-07-07 01:26:26,825 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11200, best=0.76, avg=0.75, std=0.00, steps=1.376e+08
2023-07-07 01:26:34,886 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11300, best=0.76, avg=0.75, std=0.00, steps=1.389e+08
2023-07-07 01:26:42,941 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11400, best=0.76, avg=0.75, std=0.00, steps=1.401e+08
2023-07-07 01:26:50,976 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11500, best=0.76, avg=0.75, std=0.00, steps=1.413e+08
2023-07-07 01:26:59,047 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11600, best=0.76, avg=0.75, std=0.00, steps=1.426e+08
2023-07-07 01:27:07,127 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11700, best=0.77, avg=0.76, std=0.00, steps=1.438e+08
2023-07-07 01:27:15,187 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11800, best=0.77, avg=0.76, std=0.00, steps=1.450e+08
2023-07-07 01:27:23,236 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11900, best=0.77, avg=0.76, std=0.00, steps=1.462e+08
2023-07-07 01:27:31,191 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11999, best=0.77, avg=0.76, std=0.00, steps=1.475e+08
2023-07-07 01:27:31,191 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 01:27:31,218 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 01:27:31,218 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 01:27:31,250 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 01:27:43,497 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.655e+06
2023-07-07 01:27:54,148 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=3.293e+06
2023-07-07 01:28:04,791 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=4.932e+06
2023-07-07 01:28:15,491 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=6.570e+06
2023-07-07 01:28:26,190 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=8.208e+06
2023-07-07 01:28:36,837 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=9.847e+06
2023-07-07 01:28:47,520 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=1.149e+07
2023-07-07 01:28:58,163 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 01:29:08,848 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 01:29:19,525 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.640e+07
2023-07-07 01:29:30,197 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.804e+07
2023-07-07 01:29:40,882 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.968e+07
2023-07-07 01:29:51,562 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=2.132e+07
2023-07-07 01:30:02,204 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 01:30:12,860 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 01:30:23,558 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 01:30:34,202 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=2.787e+07
2023-07-07 01:30:44,883 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.951e+07
2023-07-07 01:30:55,532 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=3.115e+07
2023-07-07 01:31:06,197 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 01:31:16,850 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 01:31:27,509 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=3.606e+07
2023-07-07 01:31:38,171 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=3.770e+07
2023-07-07 01:31:48,828 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=3.934e+07
2023-07-07 01:31:59,477 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=4.098e+07
2023-07-07 01:32:10,156 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 01:32:20,877 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 01:32:31,611 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=4.589e+07
2023-07-07 01:32:42,331 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=4.753e+07
2023-07-07 01:32:52,994 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=4.917e+07
2023-07-07 01:33:03,627 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=5.081e+07
2023-07-07 01:33:14,298 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=5.245e+07
2023-07-07 01:33:25,032 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 01:33:35,681 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=5.572e+07
2023-07-07 01:33:46,413 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=5.736e+07
2023-07-07 01:33:57,058 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=5.900e+07
2023-07-07 01:34:07,711 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=6.064e+07
2023-07-07 01:34:18,403 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=6.228e+07
2023-07-07 01:34:29,064 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 01:34:39,733 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=6.555e+07
2023-07-07 01:34:50,387 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=6.719e+07
2023-07-07 01:35:01,065 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=6.883e+07
2023-07-07 01:35:11,826 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=7.047e+07
2023-07-07 01:35:22,588 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=7.211e+07
2023-07-07 01:35:33,272 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 01:35:43,936 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=7.538e+07
2023-07-07 01:35:54,609 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=7.702e+07
2023-07-07 01:36:05,325 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 01:36:16,066 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=8.030e+07
2023-07-07 01:36:26,776 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=8.194e+07
2023-07-07 01:36:37,477 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 01:36:48,158 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=8.521e+07
2023-07-07 01:36:58,861 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=8.685e+07
2023-07-07 01:37:09,525 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 01:37:20,233 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=9.013e+07
2023-07-07 01:37:30,874 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=9.177e+07
2023-07-07 01:37:41,513 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=9.341e+07
2023-07-07 01:37:52,190 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=9.504e+07
2023-07-07 01:38:02,827 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=9.668e+07
2023-07-07 01:38:13,468 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 01:38:24,152 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=9.996e+07
2023-07-07 01:38:34,800 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=1.016e+08
2023-07-07 01:38:45,535 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 01:38:56,272 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 01:39:06,951 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=1.065e+08
2023-07-07 01:39:17,644 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=1.082e+08
2023-07-07 01:39:28,367 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=1.098e+08
2023-07-07 01:39:39,019 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=1.114e+08
2023-07-07 01:39:49,699 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 01:40:00,342 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=1.147e+08
2023-07-07 01:40:10,981 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=1.163e+08
2023-07-07 01:40:21,626 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 01:40:32,271 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=1.196e+08
2023-07-07 01:40:42,919 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=1.213e+08
2023-07-07 01:40:53,579 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 01:41:04,238 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=1.245e+08
2023-07-07 01:41:14,917 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=1.262e+08
2023-07-07 01:41:25,581 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 01:41:36,248 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=1.294e+08
2023-07-07 01:41:46,915 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=1.311e+08
2023-07-07 01:41:57,566 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=1.327e+08
2023-07-07 01:42:08,217 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.344e+08
2023-07-07 01:42:18,891 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.01, steps=1.360e+08
2023-07-07 01:42:29,526 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.376e+08
2023-07-07 01:42:40,164 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.01, steps=1.393e+08
2023-07-07 01:42:50,892 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.01, steps=1.409e+08
2023-07-07 01:43:01,633 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.01, steps=1.426e+08
2023-07-07 01:43:12,280 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.01, steps=1.442e+08
2023-07-07 01:43:22,918 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.01, steps=1.458e+08
2023-07-07 01:43:33,572 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.475e+08
2023-07-07 01:43:44,255 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9100, best=0.61, avg=0.60, std=0.00, steps=1.491e+08
2023-07-07 01:43:54,951 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9200, best=0.66, avg=0.64, std=0.00, steps=1.507e+08
2023-07-07 01:44:05,663 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9300, best=0.66, avg=0.65, std=0.00, steps=1.524e+08
2023-07-07 01:44:16,308 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9400, best=0.66, avg=0.65, std=0.00, steps=1.540e+08
2023-07-07 01:44:27,045 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9500, best=0.67, avg=0.66, std=0.00, steps=1.557e+08
2023-07-07 01:44:37,738 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9600, best=0.67, avg=0.66, std=0.00, steps=1.573e+08
2023-07-07 01:44:48,495 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9700, best=0.68, avg=0.67, std=0.00, steps=1.589e+08
2023-07-07 01:44:59,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9800, best=0.68, avg=0.67, std=0.00, steps=1.606e+08
2023-07-07 01:45:09,861 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9900, best=0.68, avg=0.67, std=0.00, steps=1.622e+08
2023-07-07 01:45:20,524 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10000, best=0.69, avg=0.68, std=0.00, steps=1.639e+08
2023-07-07 01:45:31,216 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10100, best=0.69, avg=0.68, std=0.00, steps=1.655e+08
2023-07-07 01:45:41,932 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10200, best=0.69, avg=0.68, std=0.00, steps=1.671e+08
2023-07-07 01:45:52,666 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10300, best=0.69, avg=0.68, std=0.00, steps=1.688e+08
2023-07-07 01:46:03,389 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10400, best=0.70, avg=0.69, std=0.00, steps=1.704e+08
2023-07-07 01:46:14,033 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10500, best=0.70, avg=0.69, std=0.00, steps=1.720e+08
2023-07-07 01:46:24,743 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10600, best=0.70, avg=0.69, std=0.00, steps=1.737e+08
2023-07-07 01:46:35,487 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10700, best=0.70, avg=0.69, std=0.00, steps=1.753e+08
2023-07-07 01:46:46,163 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10800, best=0.71, avg=0.69, std=0.00, steps=1.770e+08
2023-07-07 01:46:56,807 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10900, best=0.70, avg=0.70, std=0.00, steps=1.786e+08
2023-07-07 01:47:07,466 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11000, best=0.71, avg=0.70, std=0.00, steps=1.802e+08
2023-07-07 01:47:18,135 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11100, best=0.71, avg=0.70, std=0.00, steps=1.819e+08
2023-07-07 01:47:28,818 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11200, best=0.71, avg=0.70, std=0.00, steps=1.835e+08
2023-07-07 01:47:39,500 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11300, best=0.71, avg=0.70, std=0.00, steps=1.852e+08
2023-07-07 01:47:50,187 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11400, best=0.71, avg=0.70, std=0.00, steps=1.868e+08
2023-07-07 01:48:00,827 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11500, best=0.71, avg=0.70, std=0.00, steps=1.884e+08
2023-07-07 01:48:11,470 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11600, best=0.71, avg=0.70, std=0.00, steps=1.901e+08
2023-07-07 01:48:22,118 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11700, best=0.71, avg=0.70, std=0.00, steps=1.917e+08
2023-07-07 01:48:32,813 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11800, best=0.72, avg=0.71, std=0.00, steps=1.933e+08
2023-07-07 01:48:43,568 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11900, best=0.72, avg=0.71, std=0.00, steps=1.950e+08
2023-07-07 01:48:54,221 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11999, best=0.71, avg=0.71, std=0.00, steps=1.966e+08
2023-07-07 01:48:54,222 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 01:48:54,247 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 01:48:54,248 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 01:48:54,280 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 01:49:06,724 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=1.655e+06
2023-07-07 01:49:17,456 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=3.293e+06
2023-07-07 01:49:28,121 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=4.932e+06
2023-07-07 01:49:38,723 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=6.570e+06
2023-07-07 01:49:49,384 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=8.208e+06
2023-07-07 01:50:00,031 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=9.847e+06
2023-07-07 01:50:10,652 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.149e+07
2023-07-07 01:50:21,285 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.312e+07
2023-07-07 01:50:31,932 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.476e+07
2023-07-07 01:50:42,617 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=1.640e+07
2023-07-07 01:50:53,216 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=1.804e+07
2023-07-07 01:51:03,848 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=1.968e+07
2023-07-07 01:51:14,478 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.132e+07
2023-07-07 01:51:25,110 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.295e+07
2023-07-07 01:51:35,732 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=2.459e+07
2023-07-07 01:51:46,362 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 01:51:56,986 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=2.787e+07
2023-07-07 01:52:07,611 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=2.951e+07
2023-07-07 01:52:18,243 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.115e+07
2023-07-07 01:52:28,863 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=3.278e+07
2023-07-07 01:52:39,493 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=3.442e+07
2023-07-07 01:52:50,132 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=3.606e+07
2023-07-07 01:53:00,818 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=3.770e+07
2023-07-07 01:53:11,473 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=3.934e+07
2023-07-07 01:53:22,127 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=4.098e+07
2023-07-07 01:53:32,793 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=4.261e+07
2023-07-07 01:53:43,473 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=4.425e+07
2023-07-07 01:53:54,094 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=4.589e+07
2023-07-07 01:54:04,727 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=4.753e+07
2023-07-07 01:54:15,381 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=4.917e+07
2023-07-07 01:54:26,001 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=5.081e+07
2023-07-07 01:54:36,619 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=5.245e+07
2023-07-07 01:54:47,240 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=5.408e+07
2023-07-07 01:54:57,891 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=5.572e+07
2023-07-07 01:55:08,557 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=5.736e+07
2023-07-07 01:55:19,199 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=5.900e+07
2023-07-07 01:55:29,900 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=6.064e+07
2023-07-07 01:55:40,582 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=6.228e+07
2023-07-07 01:55:51,251 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=6.391e+07
2023-07-07 01:56:01,918 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=6.555e+07
2023-07-07 01:56:12,581 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=6.719e+07
2023-07-07 01:56:23,181 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.00, steps=6.883e+07
2023-07-07 01:56:33,794 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=7.047e+07
2023-07-07 01:56:44,397 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=7.211e+07
2023-07-07 01:56:55,067 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=7.374e+07
2023-07-07 01:57:05,766 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.00, steps=7.538e+07
2023-07-07 01:57:16,443 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=7.702e+07
2023-07-07 01:57:27,122 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.00, steps=7.866e+07
2023-07-07 01:57:37,739 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=8.030e+07
2023-07-07 01:57:48,329 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=8.194e+07
2023-07-07 01:57:58,917 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=8.357e+07
2023-07-07 01:58:09,502 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=8.521e+07
2023-07-07 01:58:20,123 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=8.685e+07
2023-07-07 01:58:30,747 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 01:58:41,408 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 01:58:52,136 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=9.177e+07
2023-07-07 01:59:02,741 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=9.341e+07
2023-07-07 01:59:13,362 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=9.504e+07
2023-07-07 01:59:23,996 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=9.668e+07
2023-07-07 01:59:34,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=9.832e+07
2023-07-07 01:59:45,292 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=9.996e+07
2023-07-07 01:59:55,986 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 02:00:06,649 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 02:00:17,295 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 02:00:27,965 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 02:00:38,623 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 02:00:49,299 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.098e+08
2023-07-07 02:00:59,952 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 02:01:10,593 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.131e+08
2023-07-07 02:01:21,221 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 02:01:31,841 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.163e+08
2023-07-07 02:01:42,560 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 02:01:53,182 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.196e+08
2023-07-07 02:02:03,860 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.213e+08
2023-07-07 02:02:14,523 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 02:02:25,179 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.245e+08
2023-07-07 02:02:35,886 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.262e+08
2023-07-07 02:02:46,573 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 02:02:57,227 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.294e+08
2023-07-07 02:03:07,839 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 02:03:18,441 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 02:03:29,044 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.344e+08
2023-07-07 02:03:39,682 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.360e+08
2023-07-07 02:03:50,384 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.376e+08
2023-07-07 02:04:01,094 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8500, best=0.58, avg=0.57, std=0.00, steps=1.393e+08
2023-07-07 02:04:11,723 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8600, best=0.61, avg=0.60, std=0.00, steps=1.409e+08
2023-07-07 02:04:22,374 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8700, best=0.63, avg=0.62, std=0.00, steps=1.426e+08
2023-07-07 02:04:33,014 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8800, best=0.65, avg=0.64, std=0.00, steps=1.442e+08
2023-07-07 02:04:43,651 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8900, best=0.66, avg=0.65, std=0.00, steps=1.458e+08
2023-07-07 02:04:54,282 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9000, best=0.67, avg=0.66, std=0.00, steps=1.475e+08
2023-07-07 02:05:04,979 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9100, best=0.67, avg=0.67, std=0.00, steps=1.491e+08
2023-07-07 02:05:15,697 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9200, best=0.68, avg=0.67, std=0.00, steps=1.507e+08
2023-07-07 02:05:26,398 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9300, best=0.69, avg=0.68, std=0.00, steps=1.524e+08
2023-07-07 02:05:37,078 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9400, best=0.69, avg=0.68, std=0.00, steps=1.540e+08
2023-07-07 02:05:47,690 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9500, best=0.69, avg=0.68, std=0.00, steps=1.557e+08
2023-07-07 02:05:58,328 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9600, best=0.69, avg=0.69, std=0.00, steps=1.573e+08
2023-07-07 02:06:08,968 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9700, best=0.70, avg=0.69, std=0.00, steps=1.589e+08
2023-07-07 02:06:19,598 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9800, best=0.70, avg=0.69, std=0.00, steps=1.606e+08
2023-07-07 02:06:30,220 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9900, best=0.70, avg=0.70, std=0.00, steps=1.622e+08
2023-07-07 02:06:40,853 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10000, best=0.71, avg=0.70, std=0.00, steps=1.639e+08
2023-07-07 02:06:51,466 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10100, best=0.71, avg=0.70, std=0.00, steps=1.655e+08
2023-07-07 02:07:02,111 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10200, best=0.71, avg=0.70, std=0.00, steps=1.671e+08
2023-07-07 02:07:12,742 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10300, best=0.72, avg=0.71, std=0.00, steps=1.688e+08
2023-07-07 02:07:23,397 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10400, best=0.72, avg=0.71, std=0.00, steps=1.704e+08
2023-07-07 02:07:34,007 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10500, best=0.71, avg=0.71, std=0.00, steps=1.720e+08
2023-07-07 02:07:44,650 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10600, best=0.72, avg=0.71, std=0.00, steps=1.737e+08
2023-07-07 02:07:55,292 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10700, best=0.72, avg=0.71, std=0.00, steps=1.753e+08
2023-07-07 02:08:05,931 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10800, best=0.72, avg=0.71, std=0.00, steps=1.770e+08
2023-07-07 02:08:16,565 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10900, best=0.72, avg=0.72, std=0.00, steps=1.786e+08
2023-07-07 02:08:27,185 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11000, best=0.73, avg=0.72, std=0.00, steps=1.802e+08
2023-07-07 02:08:37,813 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11100, best=0.73, avg=0.72, std=0.00, steps=1.819e+08
2023-07-07 02:08:48,462 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11200, best=0.73, avg=0.72, std=0.00, steps=1.835e+08
2023-07-07 02:08:59,100 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11300, best=0.73, avg=0.72, std=0.00, steps=1.852e+08
2023-07-07 02:09:09,734 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11400, best=0.73, avg=0.72, std=0.00, steps=1.868e+08
2023-07-07 02:09:20,389 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11500, best=0.73, avg=0.73, std=0.00, steps=1.884e+08
2023-07-07 02:09:31,090 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11600, best=0.74, avg=0.73, std=0.00, steps=1.901e+08
2023-07-07 02:09:41,732 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11700, best=0.74, avg=0.73, std=0.00, steps=1.917e+08
2023-07-07 02:09:52,337 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11800, best=0.74, avg=0.73, std=0.00, steps=1.933e+08
2023-07-07 02:10:02,954 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11900, best=0.74, avg=0.73, std=0.00, steps=1.950e+08
2023-07-07 02:10:13,463 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11999, best=0.74, avg=0.73, std=0.00, steps=1.966e+08
2023-07-07 02:10:13,464 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 02:10:13,488 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 02:10:13,488 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 02:10:13,522 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 02:10:27,029 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=1.862e+06
2023-07-07 02:10:38,965 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=3.705e+06
2023-07-07 02:10:50,928 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=5.548e+06
2023-07-07 02:11:02,957 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=7.391e+06
2023-07-07 02:11:14,917 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=9.234e+06
2023-07-07 02:11:26,890 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.108e+07
2023-07-07 02:11:38,861 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.292e+07
2023-07-07 02:11:50,812 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.476e+07
2023-07-07 02:12:02,806 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.661e+07
2023-07-07 02:12:14,817 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=1.845e+07
2023-07-07 02:12:26,779 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.029e+07
2023-07-07 02:12:38,748 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.214e+07
2023-07-07 02:12:50,707 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.398e+07
2023-07-07 02:13:02,620 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.582e+07
2023-07-07 02:13:14,595 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=2.767e+07
2023-07-07 02:13:26,570 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.951e+07
2023-07-07 02:13:38,626 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=3.135e+07
2023-07-07 02:13:50,669 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=3.320e+07
2023-07-07 02:14:02,711 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.504e+07
2023-07-07 02:14:14,694 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=3.688e+07
2023-07-07 02:14:26,674 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=3.873e+07
2023-07-07 02:14:38,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=4.057e+07
2023-07-07 02:14:50,636 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=4.241e+07
2023-07-07 02:15:02,606 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=4.426e+07
2023-07-07 02:15:14,561 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=4.610e+07
2023-07-07 02:15:26,561 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=4.794e+07
2023-07-07 02:15:38,540 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=4.978e+07
2023-07-07 02:15:50,508 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=5.163e+07
2023-07-07 02:16:02,614 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=5.347e+07
2023-07-07 02:16:14,614 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=5.531e+07
2023-07-07 02:16:26,585 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=5.716e+07
2023-07-07 02:16:38,595 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=5.900e+07
2023-07-07 02:16:50,556 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=6.084e+07
2023-07-07 02:17:02,533 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=6.269e+07
2023-07-07 02:17:14,498 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=6.453e+07
2023-07-07 02:17:26,436 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=6.637e+07
2023-07-07 02:17:38,384 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=6.822e+07
2023-07-07 02:17:50,359 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=7.006e+07
2023-07-07 02:18:02,358 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=7.190e+07
2023-07-07 02:18:14,462 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 02:18:26,530 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=7.559e+07
2023-07-07 02:18:38,608 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=7.743e+07
2023-07-07 02:18:50,625 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=7.928e+07
2023-07-07 02:19:02,678 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=8.112e+07
2023-07-07 02:19:14,734 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=8.296e+07
2023-07-07 02:19:26,741 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=8.481e+07
2023-07-07 02:19:38,713 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=8.665e+07
2023-07-07 02:19:50,680 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 02:20:02,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=9.034e+07
2023-07-07 02:20:14,636 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=9.218e+07
2023-07-07 02:20:26,733 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=9.402e+07
2023-07-07 02:20:38,786 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=9.586e+07
2023-07-07 02:20:50,789 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=9.771e+07
2023-07-07 02:21:02,764 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=9.955e+07
2023-07-07 02:21:14,745 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.014e+08
2023-07-07 02:21:26,757 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 02:21:38,692 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.051e+08
2023-07-07 02:21:50,622 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.069e+08
2023-07-07 02:22:02,563 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.088e+08
2023-07-07 02:22:14,581 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 02:22:26,569 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.125e+08
2023-07-07 02:22:38,656 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.143e+08
2023-07-07 02:22:50,626 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.161e+08
2023-07-07 02:23:02,576 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 02:23:14,521 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.198e+08
2023-07-07 02:23:26,474 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 02:23:38,429 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.235e+08
2023-07-07 02:23:50,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 02:24:02,452 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.272e+08
2023-07-07 02:24:14,435 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 02:24:26,383 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.309e+08
2023-07-07 02:24:38,345 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 02:24:50,348 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.346e+08
2023-07-07 02:25:02,411 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.364e+08
2023-07-07 02:25:14,474 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.383e+08
2023-07-07 02:25:26,439 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 02:25:38,373 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.419e+08
2023-07-07 02:25:50,305 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.438e+08
2023-07-07 02:26:02,279 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.456e+08
2023-07-07 02:26:14,262 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 02:26:26,248 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.493e+08
2023-07-07 02:26:38,225 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.512e+08
2023-07-07 02:26:50,198 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.530e+08
2023-07-07 02:27:02,164 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.548e+08
2023-07-07 02:27:14,139 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.567e+08
2023-07-07 02:27:26,124 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.585e+08
2023-07-07 02:27:38,141 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.604e+08
2023-07-07 02:27:50,121 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 02:28:02,105 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.641e+08
2023-07-07 02:28:14,100 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 02:28:26,151 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.677e+08
2023-07-07 02:28:38,139 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 02:28:50,176 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.714e+08
2023-07-07 02:29:02,134 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.733e+08
2023-07-07 02:29:14,073 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=1.751e+08
2023-07-07 02:29:26,042 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 02:29:38,024 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=1.788e+08
2023-07-07 02:29:50,002 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=1.807e+08
2023-07-07 02:30:01,976 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=1.825e+08
2023-07-07 02:30:13,939 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 02:30:25,885 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=1.862e+08
2023-07-07 02:30:37,816 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 02:30:49,761 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=1.899e+08
2023-07-07 02:31:01,701 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 02:31:13,632 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=1.936e+08
2023-07-07 02:31:25,572 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=1.954e+08
2023-07-07 02:31:37,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=1.972e+08
2023-07-07 02:31:49,555 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 02:32:01,518 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.009e+08
2023-07-07 02:32:13,472 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 02:32:25,467 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.046e+08
2023-07-07 02:32:37,510 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 02:32:49,439 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.083e+08
2023-07-07 02:33:01,385 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11400, best=0.59, avg=0.58, std=0.00, steps=2.101e+08
2023-07-07 02:33:13,324 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11500, best=0.59, avg=0.58, std=0.00, steps=2.120e+08
2023-07-07 02:33:25,276 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11600, best=0.60, avg=0.59, std=0.00, steps=2.138e+08
2023-07-07 02:33:37,232 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11700, best=0.61, avg=0.60, std=0.00, steps=2.157e+08
2023-07-07 02:33:49,236 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11800, best=0.62, avg=0.61, std=0.00, steps=2.175e+08
2023-07-07 02:34:01,256 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11900, best=0.63, avg=0.62, std=0.00, steps=2.194e+08
2023-07-07 02:34:13,092 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11999, best=0.64, avg=0.63, std=0.00, steps=2.212e+08
2023-07-07 02:34:13,092 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 02:34:13,117 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 02:34:13,117 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 02:34:13,149 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 02:34:27,990 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=2.068e+06
2023-07-07 02:34:41,242 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=4.116e+06
2023-07-07 02:34:54,507 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=6.164e+06
2023-07-07 02:35:07,759 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=8.212e+06
2023-07-07 02:35:21,096 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.026e+07
2023-07-07 02:35:34,408 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.231e+07
2023-07-07 02:35:47,779 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.436e+07
2023-07-07 02:36:01,112 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.640e+07
2023-07-07 02:36:14,386 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.845e+07
2023-07-07 02:36:27,686 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=2.050e+07
2023-07-07 02:36:40,966 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.255e+07
2023-07-07 02:36:54,210 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.460e+07
2023-07-07 02:37:07,462 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.664e+07
2023-07-07 02:37:20,730 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.869e+07
2023-07-07 02:37:34,053 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=3.074e+07
2023-07-07 02:37:47,400 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=3.279e+07
2023-07-07 02:38:00,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=3.484e+07
2023-07-07 02:38:13,965 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=3.688e+07
2023-07-07 02:38:27,233 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.893e+07
2023-07-07 02:38:40,502 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=4.098e+07
2023-07-07 02:38:53,765 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=4.303e+07
2023-07-07 02:39:07,062 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=4.508e+07
2023-07-07 02:39:20,421 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=4.712e+07
2023-07-07 02:39:33,770 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=4.917e+07
2023-07-07 02:39:47,283 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=5.122e+07
2023-07-07 02:40:00,667 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=5.327e+07
2023-07-07 02:40:14,002 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=5.532e+07
2023-07-07 02:40:27,371 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=5.736e+07
2023-07-07 02:40:40,625 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=5.941e+07
2023-07-07 02:40:53,904 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=6.146e+07
2023-07-07 02:41:07,213 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=6.351e+07
2023-07-07 02:41:20,498 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=6.556e+07
2023-07-07 02:41:33,743 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=6.760e+07
2023-07-07 02:41:47,100 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=6.965e+07
2023-07-07 02:42:00,358 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=7.170e+07
2023-07-07 02:42:13,687 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 02:42:27,071 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=7.580e+07
2023-07-07 02:42:40,426 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=7.784e+07
2023-07-07 02:42:53,739 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=7.989e+07
2023-07-07 02:43:07,036 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=8.194e+07
2023-07-07 02:43:20,325 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=8.399e+07
2023-07-07 02:43:33,548 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=8.604e+07
2023-07-07 02:43:46,774 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=8.808e+07
2023-07-07 02:44:00,004 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 02:44:13,223 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=9.218e+07
2023-07-07 02:44:26,444 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=9.423e+07
2023-07-07 02:44:39,665 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=9.628e+07
2023-07-07 02:44:52,889 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=9.832e+07
2023-07-07 02:45:06,220 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.004e+08
2023-07-07 02:45:19,560 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.024e+08
2023-07-07 02:45:32,834 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 02:45:46,112 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 02:45:59,387 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.086e+08
2023-07-07 02:46:12,727 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 02:46:26,012 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.127e+08
2023-07-07 02:46:39,381 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 02:46:52,671 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.168e+08
2023-07-07 02:47:06,067 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.188e+08
2023-07-07 02:47:19,392 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.209e+08
2023-07-07 02:47:32,661 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 02:47:45,943 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.249e+08
2023-07-07 02:47:59,209 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.270e+08
2023-07-07 02:48:12,468 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 02:48:25,745 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 02:48:39,115 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.331e+08
2023-07-07 02:48:52,387 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 02:49:05,641 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.372e+08
2023-07-07 02:49:18,904 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 02:49:32,171 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.413e+08
2023-07-07 02:49:45,405 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.434e+08
2023-07-07 02:49:58,623 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.454e+08
2023-07-07 02:50:11,835 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 02:50:25,068 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.495e+08
2023-07-07 02:50:38,302 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.516e+08
2023-07-07 02:50:51,537 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.536e+08
2023-07-07 02:51:04,802 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.557e+08
2023-07-07 02:51:18,064 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.577e+08
2023-07-07 02:51:31,342 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 02:51:44,580 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.618e+08
2023-07-07 02:51:57,820 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 02:52:11,065 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 02:52:24,293 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.680e+08
2023-07-07 02:52:37,605 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.700e+08
2023-07-07 02:52:50,867 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 02:53:04,229 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.741e+08
2023-07-07 02:53:17,573 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.761e+08
2023-07-07 02:53:30,909 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.782e+08
2023-07-07 02:53:44,174 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.802e+08
2023-07-07 02:53:57,477 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.823e+08
2023-07-07 02:54:10,732 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 02:54:24,024 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.864e+08
2023-07-07 02:54:37,407 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.884e+08
2023-07-07 02:54:50,679 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.905e+08
2023-07-07 02:55:04,007 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.925e+08
2023-07-07 02:55:17,282 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=1.946e+08
2023-07-07 02:55:30,574 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 02:55:43,917 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=1.987e+08
2023-07-07 02:55:57,151 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=2.007e+08
2023-07-07 02:56:10,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 02:56:23,653 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=2.048e+08
2023-07-07 02:56:36,937 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=2.069e+08
2023-07-07 02:56:50,189 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 02:57:03,490 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.110e+08
2023-07-07 02:57:16,779 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 02:57:30,131 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.151e+08
2023-07-07 02:57:43,526 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10600, best=0.59, avg=0.58, std=0.00, steps=2.171e+08
2023-07-07 02:57:56,852 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10700, best=0.62, avg=0.61, std=0.00, steps=2.192e+08
2023-07-07 02:58:10,154 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10800, best=0.63, avg=0.62, std=0.00, steps=2.212e+08
2023-07-07 02:58:23,544 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10900, best=0.63, avg=0.63, std=0.00, steps=2.233e+08
2023-07-07 02:58:36,871 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11000, best=0.64, avg=0.64, std=0.00, steps=2.253e+08
2023-07-07 02:58:50,240 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11100, best=0.65, avg=0.64, std=0.00, steps=2.273e+08
2023-07-07 02:59:03,454 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11200, best=0.65, avg=0.64, std=0.00, steps=2.294e+08
2023-07-07 02:59:16,679 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11300, best=0.65, avg=0.65, std=0.00, steps=2.314e+08
2023-07-07 02:59:29,940 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11400, best=0.65, avg=0.65, std=0.00, steps=2.335e+08
2023-07-07 02:59:43,188 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11500, best=0.66, avg=0.65, std=0.00, steps=2.355e+08
2023-07-07 02:59:56,499 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11600, best=0.66, avg=0.65, std=0.00, steps=2.376e+08
2023-07-07 03:00:09,875 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11700, best=0.66, avg=0.65, std=0.00, steps=2.396e+08
2023-07-07 03:00:23,229 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11800, best=0.67, avg=0.66, std=0.00, steps=2.417e+08
2023-07-07 03:00:36,673 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11900, best=0.67, avg=0.66, std=0.00, steps=2.437e+08
2023-07-07 03:00:49,833 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11999, best=0.67, avg=0.66, std=0.00, steps=2.458e+08
2023-07-07 03:00:49,833 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 03:00:49,858 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 03:00:49,858 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 03:00:49,889 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 03:01:07,434 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=2.482e+06
2023-07-07 03:01:23,267 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=4.940e+06
2023-07-07 03:01:39,079 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=7.397e+06
2023-07-07 03:01:54,968 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=9.855e+06
2023-07-07 03:02:10,885 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.231e+07
2023-07-07 03:02:26,751 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.477e+07
2023-07-07 03:02:42,641 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.723e+07
2023-07-07 03:02:58,646 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.969e+07
2023-07-07 03:03:14,525 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=2.214e+07
2023-07-07 03:03:30,354 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=2.460e+07
2023-07-07 03:03:46,171 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.706e+07
2023-07-07 03:04:02,065 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.952e+07
2023-07-07 03:04:17,974 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=3.197e+07
2023-07-07 03:04:33,906 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=3.443e+07
2023-07-07 03:04:49,805 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=3.689e+07
2023-07-07 03:05:05,803 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=3.935e+07
2023-07-07 03:05:21,654 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=4.180e+07
2023-07-07 03:05:37,529 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=4.426e+07
2023-07-07 03:05:53,376 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=4.672e+07
2023-07-07 03:06:09,192 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=4.918e+07
2023-07-07 03:06:25,058 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=5.163e+07
2023-07-07 03:06:40,939 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=5.409e+07
2023-07-07 03:06:56,868 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=5.655e+07
2023-07-07 03:07:12,672 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=5.901e+07
2023-07-07 03:07:28,473 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=6.146e+07
2023-07-07 03:07:44,277 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=6.392e+07
2023-07-07 03:08:00,206 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=6.638e+07
2023-07-07 03:08:16,043 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=6.884e+07
2023-07-07 03:08:31,845 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=7.129e+07
2023-07-07 03:08:47,683 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 03:09:03,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=7.621e+07
2023-07-07 03:09:19,399 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=7.867e+07
2023-07-07 03:09:35,219 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=8.113e+07
2023-07-07 03:09:51,040 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=8.358e+07
2023-07-07 03:10:06,895 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=8.604e+07
2023-07-07 03:10:22,728 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=8.850e+07
2023-07-07 03:10:38,563 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=9.096e+07
2023-07-07 03:10:54,419 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=9.341e+07
2023-07-07 03:11:10,270 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=9.587e+07
2023-07-07 03:11:26,104 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=9.833e+07
2023-07-07 03:11:41,896 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.008e+08
2023-07-07 03:11:57,714 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 03:12:13,542 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.057e+08
2023-07-07 03:12:29,454 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 03:12:45,317 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 03:13:01,244 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.131e+08
2023-07-07 03:13:17,201 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.155e+08
2023-07-07 03:13:33,117 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 03:13:49,058 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.204e+08
2023-07-07 03:14:04,934 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 03:14:20,736 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 03:14:36,625 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 03:14:52,486 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.303e+08
2023-07-07 03:15:08,463 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 03:15:24,446 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 03:15:40,326 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.377e+08
2023-07-07 03:15:56,205 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 03:16:12,074 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.426e+08
2023-07-07 03:16:28,028 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.450e+08
2023-07-07 03:16:43,956 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 03:16:59,909 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.499e+08
2023-07-07 03:17:15,724 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.524e+08
2023-07-07 03:17:31,668 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.549e+08
2023-07-07 03:17:47,568 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.573e+08
2023-07-07 03:18:03,440 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 03:18:19,234 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 03:18:35,033 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.647e+08
2023-07-07 03:18:50,965 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.671e+08
2023-07-07 03:19:06,876 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 03:19:22,752 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 03:19:38,624 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.745e+08
2023-07-07 03:19:54,485 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 03:20:10,345 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.794e+08
2023-07-07 03:20:26,195 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.819e+08
2023-07-07 03:20:42,072 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 03:20:57,931 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.868e+08
2023-07-07 03:21:13,784 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.893e+08
2023-07-07 03:21:29,639 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 03:21:45,569 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.942e+08
2023-07-07 03:22:01,558 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 03:22:17,506 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 03:22:33,343 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.015e+08
2023-07-07 03:22:49,218 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.040e+08
2023-07-07 03:23:05,059 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 03:23:20,987 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 03:23:36,999 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.114e+08
2023-07-07 03:23:52,984 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=2.138e+08
2023-07-07 03:24:08,821 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=2.163e+08
2023-07-07 03:24:24,846 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.188e+08
2023-07-07 03:24:40,821 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 03:24:56,717 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=2.237e+08
2023-07-07 03:25:12,667 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=2.261e+08
2023-07-07 03:25:28,480 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=2.286e+08
2023-07-07 03:25:44,428 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=2.310e+08
2023-07-07 03:26:00,359 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=2.335e+08
2023-07-07 03:26:16,221 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 03:26:32,140 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=2.384e+08
2023-07-07 03:26:48,011 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=2.409e+08
2023-07-07 03:27:03,947 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=2.433e+08
2023-07-07 03:27:19,877 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 03:27:35,833 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=2.482e+08
2023-07-07 03:27:51,749 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 03:28:07,719 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.532e+08
2023-07-07 03:28:23,631 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 03:28:39,495 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 03:28:55,410 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=2.605e+08
2023-07-07 03:29:11,379 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=2.630e+08
2023-07-07 03:29:27,304 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=2.654e+08
2023-07-07 03:29:43,158 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.679e+08
2023-07-07 03:29:58,941 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.704e+08
2023-07-07 03:30:14,755 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.728e+08
2023-07-07 03:30:30,575 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 03:30:46,396 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.777e+08
2023-07-07 03:31:02,312 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=2.802e+08
2023-07-07 03:31:18,187 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=2.826e+08
2023-07-07 03:31:34,032 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 03:31:49,869 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=2.876e+08
2023-07-07 03:32:05,719 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=2.900e+08
2023-07-07 03:32:21,690 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=2.925e+08
2023-07-07 03:32:37,517 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 03:32:37,517 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 03:32:37,541 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 03:32:37,542 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 03:32:37,573 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 03:33:00,568 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.310e+06
2023-07-07 03:33:21,692 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=6.586e+06
2023-07-07 03:33:42,664 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=9.863e+06
2023-07-07 03:34:03,715 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.314e+07
2023-07-07 03:34:24,812 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.642e+07
2023-07-07 03:34:46,211 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.969e+07
2023-07-07 03:35:07,372 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.297e+07
2023-07-07 03:35:28,505 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.625e+07
2023-07-07 03:35:49,506 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=2.952e+07
2023-07-07 03:36:10,498 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.280e+07
2023-07-07 03:36:31,491 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=3.608e+07
2023-07-07 03:36:52,613 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=3.935e+07
2023-07-07 03:37:13,764 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.263e+07
2023-07-07 03:37:34,797 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=4.591e+07
2023-07-07 03:37:55,822 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=4.918e+07
2023-07-07 03:38:16,855 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.246e+07
2023-07-07 03:38:37,913 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=5.574e+07
2023-07-07 03:38:58,936 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=5.902e+07
2023-07-07 03:39:19,983 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=6.229e+07
2023-07-07 03:39:41,029 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=6.557e+07
2023-07-07 03:40:02,044 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=6.885e+07
2023-07-07 03:40:23,065 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=7.212e+07
2023-07-07 03:40:44,113 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=7.540e+07
2023-07-07 03:41:05,209 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=7.868e+07
2023-07-07 03:41:26,268 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=8.195e+07
2023-07-07 03:41:47,329 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=8.523e+07
2023-07-07 03:42:08,442 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=8.851e+07
2023-07-07 03:42:29,571 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=9.178e+07
2023-07-07 03:42:50,716 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=9.506e+07
2023-07-07 03:43:11,865 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=9.834e+07
2023-07-07 03:43:32,971 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 03:43:53,970 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 03:44:15,020 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 03:44:36,104 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 03:44:57,170 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 03:45:18,213 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 03:45:39,206 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.213e+08
2023-07-07 03:46:00,213 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.246e+08
2023-07-07 03:46:21,238 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 03:46:42,223 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 03:47:03,307 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.344e+08
2023-07-07 03:47:24,464 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.377e+08
2023-07-07 03:47:45,537 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.409e+08
2023-07-07 03:48:06,586 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.442e+08
2023-07-07 03:48:27,810 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 03:48:48,902 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.508e+08
2023-07-07 03:49:09,939 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.540e+08
2023-07-07 03:49:31,116 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.573e+08
2023-07-07 03:49:52,235 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.606e+08
2023-07-07 03:50:13,426 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 03:50:34,556 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.671e+08
2023-07-07 03:50:55,587 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.704e+08
2023-07-07 03:51:16,660 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.737e+08
2023-07-07 03:51:37,726 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 03:51:58,786 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.803e+08
2023-07-07 03:52:19,827 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.835e+08
2023-07-07 03:52:40,864 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.868e+08
2023-07-07 03:53:01,940 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.901e+08
2023-07-07 03:53:23,059 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.934e+08
2023-07-07 03:53:44,040 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 03:54:05,163 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.999e+08
2023-07-07 03:54:26,261 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.032e+08
2023-07-07 03:54:47,295 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 03:55:08,402 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.097e+08
2023-07-07 03:55:29,514 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 03:55:50,648 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.163e+08
2023-07-07 03:56:11,846 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.196e+08
2023-07-07 03:56:32,992 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 03:56:54,059 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.261e+08
2023-07-07 03:57:15,187 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.294e+08
2023-07-07 03:57:36,290 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.327e+08
2023-07-07 03:57:57,357 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 03:58:18,432 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.392e+08
2023-07-07 03:58:39,494 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.425e+08
2023-07-07 03:59:00,562 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 03:59:21,645 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.491e+08
2023-07-07 03:59:42,886 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.523e+08
2023-07-07 04:00:03,972 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 04:00:25,160 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.589e+08
2023-07-07 04:00:46,166 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.622e+08
2023-07-07 04:01:07,268 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.655e+08
2023-07-07 04:01:28,502 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.687e+08
2023-07-07 04:01:49,604 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.720e+08
2023-07-07 04:02:10,653 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 04:02:31,738 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 04:02:52,800 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.818e+08
2023-07-07 04:03:13,921 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 04:03:35,044 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=2.884e+08
2023-07-07 04:03:56,100 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.917e+08
2023-07-07 04:04:17,146 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 04:04:38,150 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=2.982e+08
2023-07-07 04:04:59,189 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.015e+08
2023-07-07 04:05:20,212 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.048e+08
2023-07-07 04:05:41,274 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.081e+08
2023-07-07 04:06:02,451 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 04:06:23,656 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.146e+08
2023-07-07 04:06:44,814 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.179e+08
2023-07-07 04:07:05,881 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.212e+08
2023-07-07 04:07:27,093 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.244e+08
2023-07-07 04:07:48,215 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.277e+08
2023-07-07 04:08:09,233 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.310e+08
2023-07-07 04:08:30,437 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 04:08:51,592 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.375e+08
2023-07-07 04:09:12,855 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.408e+08
2023-07-07 04:09:34,025 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.441e+08
2023-07-07 04:09:55,131 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.474e+08
2023-07-07 04:10:16,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.507e+08
2023-07-07 04:10:37,384 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.539e+08
2023-07-07 04:10:58,533 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=3.572e+08
2023-07-07 04:11:19,589 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=3.605e+08
2023-07-07 04:11:40,762 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=3.638e+08
2023-07-07 04:12:01,924 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=3.670e+08
2023-07-07 04:12:23,045 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=3.703e+08
2023-07-07 04:12:44,166 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=3.736e+08
2023-07-07 04:13:05,214 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=3.769e+08
2023-07-07 04:13:26,227 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=3.801e+08
2023-07-07 04:13:47,427 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=3.834e+08
2023-07-07 04:14:08,673 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=3.867e+08
2023-07-07 04:14:29,895 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=3.900e+08
2023-07-07 04:14:50,691 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=3.932e+08
2023-07-07 04:14:50,692 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 04:14:50,716 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 04:14:50,717 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 04:14:50,750 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 04:15:14,817 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.516e+06
2023-07-07 04:15:37,114 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=6.998e+06
2023-07-07 04:15:59,602 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.048e+07
2023-07-07 04:16:22,059 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.396e+07
2023-07-07 04:16:44,424 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.744e+07
2023-07-07 04:17:06,823 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.092e+07
2023-07-07 04:17:29,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.441e+07
2023-07-07 04:17:51,675 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.789e+07
2023-07-07 04:18:14,036 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.137e+07
2023-07-07 04:18:36,474 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.485e+07
2023-07-07 04:18:58,984 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=3.833e+07
2023-07-07 04:19:21,371 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.181e+07
2023-07-07 04:19:43,741 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.530e+07
2023-07-07 04:20:06,080 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=4.878e+07
2023-07-07 04:20:28,550 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=5.226e+07
2023-07-07 04:20:50,881 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.574e+07
2023-07-07 04:21:13,357 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=5.922e+07
2023-07-07 04:21:35,790 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=6.270e+07
2023-07-07 04:21:58,271 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=6.619e+07
2023-07-07 04:22:20,684 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=6.967e+07
2023-07-07 04:22:42,946 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=7.315e+07
2023-07-07 04:23:05,267 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=7.663e+07
2023-07-07 04:23:27,756 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=8.011e+07
2023-07-07 04:23:50,148 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=8.359e+07
2023-07-07 04:24:12,711 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=8.707e+07
2023-07-07 04:24:35,037 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=9.056e+07
2023-07-07 04:24:57,523 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=9.404e+07
2023-07-07 04:25:19,782 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=9.752e+07
2023-07-07 04:25:42,063 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.010e+08
2023-07-07 04:26:04,530 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 04:26:26,991 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.080e+08
2023-07-07 04:26:49,362 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 04:27:11,636 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.149e+08
2023-07-07 04:27:33,968 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.184e+08
2023-07-07 04:27:56,242 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.219e+08
2023-07-07 04:28:18,661 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 04:28:40,992 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.289e+08
2023-07-07 04:29:03,375 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.323e+08
2023-07-07 04:29:25,840 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.358e+08
2023-07-07 04:29:48,342 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 04:30:10,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.428e+08
2023-07-07 04:30:33,079 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.463e+08
2023-07-07 04:30:55,510 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.497e+08
2023-07-07 04:31:17,816 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.532e+08
2023-07-07 04:31:40,180 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.567e+08
2023-07-07 04:32:02,522 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.602e+08
2023-07-07 04:32:25,043 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.637e+08
2023-07-07 04:32:47,515 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.672e+08
2023-07-07 04:33:09,874 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.706e+08
2023-07-07 04:33:32,234 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.741e+08
2023-07-07 04:33:54,701 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.776e+08
2023-07-07 04:34:17,093 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.811e+08
2023-07-07 04:34:39,684 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.846e+08
2023-07-07 04:35:02,217 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 04:35:24,721 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.915e+08
2023-07-07 04:35:47,020 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.950e+08
2023-07-07 04:36:09,405 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.985e+08
2023-07-07 04:36:31,718 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.020e+08
2023-07-07 04:36:54,002 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.054e+08
2023-07-07 04:37:16,334 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 04:37:38,627 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.124e+08
2023-07-07 04:38:00,911 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.159e+08
2023-07-07 04:38:23,211 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.194e+08
2023-07-07 04:38:45,556 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 04:39:08,063 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.263e+08
2023-07-07 04:39:30,603 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.298e+08
2023-07-07 04:39:53,112 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.333e+08
2023-07-07 04:40:15,600 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.368e+08
2023-07-07 04:40:38,035 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.403e+08
2023-07-07 04:41:00,385 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.437e+08
2023-07-07 04:41:22,655 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.472e+08
2023-07-07 04:41:44,970 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 04:42:07,272 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.542e+08
2023-07-07 04:42:29,626 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.577e+08
2023-07-07 04:42:51,970 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.612e+08
2023-07-07 04:43:14,330 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.646e+08
2023-07-07 04:43:36,668 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.681e+08
2023-07-07 04:43:59,161 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.716e+08
2023-07-07 04:44:21,620 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.751e+08
2023-07-07 04:44:43,982 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 04:45:06,489 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.820e+08
2023-07-07 04:45:28,863 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.855e+08
2023-07-07 04:45:51,200 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.890e+08
2023-07-07 04:46:13,652 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.925e+08
2023-07-07 04:46:36,101 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.960e+08
2023-07-07 04:46:58,380 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.995e+08
2023-07-07 04:47:20,657 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.029e+08
2023-07-07 04:47:43,087 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.064e+08
2023-07-07 04:48:05,602 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.099e+08
2023-07-07 04:48:27,956 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.134e+08
2023-07-07 04:48:50,275 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.169e+08
2023-07-07 04:49:12,610 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.203e+08
2023-07-07 04:49:34,955 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.238e+08
2023-07-07 04:49:57,396 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.273e+08
2023-07-07 04:50:19,734 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.308e+08
2023-07-07 04:50:42,077 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 04:51:04,448 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.378e+08
2023-07-07 04:51:26,850 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.412e+08
2023-07-07 04:51:49,323 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.447e+08
2023-07-07 04:52:11,735 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.482e+08
2023-07-07 04:52:34,041 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.517e+08
2023-07-07 04:52:56,317 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.552e+08
2023-07-07 04:53:18,855 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.586e+08
2023-07-07 04:53:41,381 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.621e+08
2023-07-07 04:54:03,651 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.656e+08
2023-07-07 04:54:26,044 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.691e+08
2023-07-07 04:54:48,512 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.726e+08
2023-07-07 04:55:10,843 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 04:55:33,266 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=3.795e+08
2023-07-07 04:55:55,747 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=3.830e+08
2023-07-07 04:56:18,293 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=3.865e+08
2023-07-07 04:56:40,818 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=3.900e+08
2023-07-07 04:57:03,111 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=3.935e+08
2023-07-07 04:57:25,408 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=3.969e+08
2023-07-07 04:57:47,734 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.004e+08
2023-07-07 04:58:10,189 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.039e+08
2023-07-07 04:58:32,597 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.074e+08
2023-07-07 04:58:55,049 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.109e+08
2023-07-07 04:59:17,392 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.143e+08
2023-07-07 04:59:39,512 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.178e+08
2023-07-07 04:59:39,513 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 04:59:39,538 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 04:59:39,538 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 04:59:39,571 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 05:00:05,108 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.723e+06
2023-07-07 05:00:28,809 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=7.410e+06
2023-07-07 05:00:52,628 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.110e+07
2023-07-07 05:01:16,419 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.478e+07
2023-07-07 05:01:40,145 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.847e+07
2023-07-07 05:02:03,770 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.216e+07
2023-07-07 05:02:27,422 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.584e+07
2023-07-07 05:02:50,996 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.953e+07
2023-07-07 05:03:14,846 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.321e+07
2023-07-07 05:03:38,526 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.690e+07
2023-07-07 05:04:02,165 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=4.059e+07
2023-07-07 05:04:25,885 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.427e+07
2023-07-07 05:04:49,625 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.796e+07
2023-07-07 05:05:13,198 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=5.165e+07
2023-07-07 05:05:36,777 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=5.533e+07
2023-07-07 05:06:00,467 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.902e+07
2023-07-07 05:06:24,252 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=6.271e+07
2023-07-07 05:06:48,030 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=6.639e+07
2023-07-07 05:07:11,804 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=7.008e+07
2023-07-07 05:07:35,644 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=7.376e+07
2023-07-07 05:07:59,387 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=7.745e+07
2023-07-07 05:08:23,057 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=8.114e+07
2023-07-07 05:08:46,782 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=8.482e+07
2023-07-07 05:09:10,557 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=8.851e+07
2023-07-07 05:09:34,364 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=9.220e+07
2023-07-07 05:09:58,222 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=9.588e+07
2023-07-07 05:10:22,012 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=9.957e+07
2023-07-07 05:10:45,784 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=1.033e+08
2023-07-07 05:11:09,606 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.069e+08
2023-07-07 05:11:33,325 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 05:11:57,031 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.143e+08
2023-07-07 05:12:20,824 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 05:12:44,495 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 05:13:08,139 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 05:13:31,700 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.291e+08
2023-07-07 05:13:55,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 05:14:18,959 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.364e+08
2023-07-07 05:14:42,706 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 05:15:06,321 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.438e+08
2023-07-07 05:15:29,982 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 05:15:53,586 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.512e+08
2023-07-07 05:16:17,254 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.549e+08
2023-07-07 05:16:40,967 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.586e+08
2023-07-07 05:17:04,666 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 05:17:28,282 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 05:17:51,905 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 05:18:15,569 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.733e+08
2023-07-07 05:18:39,228 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 05:19:02,775 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.807e+08
2023-07-07 05:19:26,340 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.844e+08
2023-07-07 05:19:49,933 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 05:20:13,519 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 05:20:37,151 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.954e+08
2023-07-07 05:21:00,790 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 05:21:24,394 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 05:21:48,045 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 05:22:11,759 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=2.102e+08
2023-07-07 05:22:35,488 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.138e+08
2023-07-07 05:22:59,255 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.175e+08
2023-07-07 05:23:22,921 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 05:23:46,646 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.249e+08
2023-07-07 05:24:10,388 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.286e+08
2023-07-07 05:24:34,076 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.323e+08
2023-07-07 05:24:57,716 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 05:25:21,395 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.397e+08
2023-07-07 05:25:45,201 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.433e+08
2023-07-07 05:26:08,807 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.470e+08
2023-07-07 05:26:32,411 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 05:26:56,222 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.544e+08
2023-07-07 05:27:19,954 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 05:27:43,784 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.618e+08
2023-07-07 05:28:07,545 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.655e+08
2023-07-07 05:28:31,294 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.691e+08
2023-07-07 05:28:54,967 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.728e+08
2023-07-07 05:29:18,594 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.765e+08
2023-07-07 05:29:42,371 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.802e+08
2023-07-07 05:30:06,046 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.839e+08
2023-07-07 05:30:29,686 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.876e+08
2023-07-07 05:30:53,407 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.913e+08
2023-07-07 05:31:17,237 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 05:31:41,072 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.986e+08
2023-07-07 05:32:04,828 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=3.023e+08
2023-07-07 05:32:28,576 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=3.060e+08
2023-07-07 05:32:52,398 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=3.097e+08
2023-07-07 05:33:16,206 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=3.134e+08
2023-07-07 05:33:39,951 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=3.171e+08
2023-07-07 05:34:03,541 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.208e+08
2023-07-07 05:34:27,247 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.244e+08
2023-07-07 05:34:50,979 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.281e+08
2023-07-07 05:35:14,718 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.318e+08
2023-07-07 05:35:38,411 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.355e+08
2023-07-07 05:36:02,054 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.392e+08
2023-07-07 05:36:25,709 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.429e+08
2023-07-07 05:36:49,427 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.466e+08
2023-07-07 05:37:13,081 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.502e+08
2023-07-07 05:37:36,873 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.539e+08
2023-07-07 05:38:00,551 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.576e+08
2023-07-07 05:38:24,136 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.613e+08
2023-07-07 05:38:47,720 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.650e+08
2023-07-07 05:39:11,528 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.687e+08
2023-07-07 05:39:35,329 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.724e+08
2023-07-07 05:39:59,090 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 05:40:22,885 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.797e+08
2023-07-07 05:40:46,683 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.834e+08
2023-07-07 05:41:10,303 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.871e+08
2023-07-07 05:41:34,094 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.908e+08
2023-07-07 05:41:57,858 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.945e+08
2023-07-07 05:42:21,597 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.982e+08
2023-07-07 05:42:45,249 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=4.019e+08
2023-07-07 05:43:09,108 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 05:43:32,846 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=4.092e+08
2023-07-07 05:43:56,684 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=4.129e+08
2023-07-07 05:44:20,389 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=4.166e+08
2023-07-07 05:44:44,148 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=4.203e+08
2023-07-07 05:45:07,765 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.240e+08
2023-07-07 05:45:31,423 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.277e+08
2023-07-07 05:45:55,124 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.313e+08
2023-07-07 05:46:18,818 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.350e+08
2023-07-07 05:46:42,461 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.387e+08
2023-07-07 05:47:05,821 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.424e+08
2023-07-07 05:47:05,822 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 05:47:05,846 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 05:47:05,846 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 05:47:05,877 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 05:47:33,854 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=4.137e+06
2023-07-07 05:48:00,121 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=8.233e+06
2023-07-07 05:48:26,396 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.233e+07
2023-07-07 05:48:52,733 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.642e+07
2023-07-07 05:49:19,112 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=2.052e+07
2023-07-07 05:49:45,527 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.462e+07
2023-07-07 05:50:11,760 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.871e+07
2023-07-07 05:50:38,037 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=3.281e+07
2023-07-07 05:51:04,350 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.690e+07
2023-07-07 05:51:30,531 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=4.100e+07
2023-07-07 05:51:56,871 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=4.510e+07
2023-07-07 05:52:23,192 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.919e+07
2023-07-07 05:52:49,443 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=5.329e+07
2023-07-07 05:53:15,797 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=5.738e+07
2023-07-07 05:53:42,135 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=6.148e+07
2023-07-07 05:54:08,502 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=6.558e+07
2023-07-07 05:54:34,899 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=6.967e+07
2023-07-07 05:55:01,176 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=7.377e+07
2023-07-07 05:55:27,394 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=7.786e+07
2023-07-07 05:55:53,696 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=8.196e+07
2023-07-07 05:56:20,021 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=8.606e+07
2023-07-07 05:56:46,460 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=9.015e+07
2023-07-07 05:57:12,925 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=9.425e+07
2023-07-07 05:57:39,309 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=9.834e+07
2023-07-07 05:58:05,703 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=1.024e+08
2023-07-07 05:58:31,886 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 05:58:58,266 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 05:59:24,588 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 05:59:50,808 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.188e+08
2023-07-07 06:00:17,134 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 06:00:43,520 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.270e+08
2023-07-07 06:01:09,791 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 06:01:35,940 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 06:02:02,090 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 06:02:28,298 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.434e+08
2023-07-07 06:02:54,568 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 06:03:20,846 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.516e+08
2023-07-07 06:03:47,343 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.557e+08
2023-07-07 06:04:13,605 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 06:04:39,909 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 06:05:06,319 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.680e+08
2023-07-07 06:05:32,555 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 06:05:58,784 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.762e+08
2023-07-07 06:06:24,922 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.803e+08
2023-07-07 06:06:51,111 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.844e+08
2023-07-07 06:07:17,354 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.885e+08
2023-07-07 06:07:43,643 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.926e+08
2023-07-07 06:08:09,775 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 06:08:35,981 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=2.007e+08
2023-07-07 06:09:02,210 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=2.048e+08
2023-07-07 06:09:28,424 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 06:09:55,055 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 06:10:21,527 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=2.171e+08
2023-07-07 06:10:47,925 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 06:11:14,176 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=2.253e+08
2023-07-07 06:11:40,404 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=2.294e+08
2023-07-07 06:12:06,647 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=2.335e+08
2023-07-07 06:12:32,866 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.376e+08
2023-07-07 06:12:59,074 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.417e+08
2023-07-07 06:13:25,286 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 06:13:51,537 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.499e+08
2023-07-07 06:14:17,740 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.540e+08
2023-07-07 06:14:43,948 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 06:15:10,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.622e+08
2023-07-07 06:15:36,449 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.663e+08
2023-07-07 06:16:02,685 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.704e+08
2023-07-07 06:16:28,913 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.745e+08
2023-07-07 06:16:55,052 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 06:17:21,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.827e+08
2023-07-07 06:17:47,511 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.868e+08
2023-07-07 06:18:13,824 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.909e+08
2023-07-07 06:18:40,043 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.950e+08
2023-07-07 06:19:06,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.990e+08
2023-07-07 06:19:32,491 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=3.031e+08
2023-07-07 06:19:58,735 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=3.072e+08
2023-07-07 06:20:24,955 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 06:20:51,269 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=3.154e+08
2023-07-07 06:21:17,534 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=3.195e+08
2023-07-07 06:21:43,690 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=3.236e+08
2023-07-07 06:22:10,027 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=3.277e+08
2023-07-07 06:22:36,498 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=3.318e+08
2023-07-07 06:23:02,730 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=3.359e+08
2023-07-07 06:23:29,000 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=3.400e+08
2023-07-07 06:23:55,393 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=3.441e+08
2023-07-07 06:24:21,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=3.482e+08
2023-07-07 06:24:48,194 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=3.523e+08
2023-07-07 06:25:14,558 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.564e+08
2023-07-07 06:25:40,848 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.605e+08
2023-07-07 06:26:07,050 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.646e+08
2023-07-07 06:26:33,323 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.687e+08
2023-07-07 06:26:59,668 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.728e+08
2023-07-07 06:27:25,854 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.769e+08
2023-07-07 06:27:52,205 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.810e+08
2023-07-07 06:28:18,368 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.851e+08
2023-07-07 06:28:44,698 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.892e+08
2023-07-07 06:29:11,023 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.933e+08
2023-07-07 06:29:37,195 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.974e+08
2023-07-07 06:30:03,292 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=4.014e+08
2023-07-07 06:30:29,549 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 06:30:55,953 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=4.096e+08
2023-07-07 06:31:22,310 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=4.137e+08
2023-07-07 06:31:48,495 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=4.178e+08
2023-07-07 06:32:14,708 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=4.219e+08
2023-07-07 06:32:41,060 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=4.260e+08
2023-07-07 06:33:07,435 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=4.301e+08
2023-07-07 06:33:33,721 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=4.342e+08
2023-07-07 06:33:59,919 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=4.383e+08
2023-07-07 06:34:26,083 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=4.424e+08
2023-07-07 06:34:52,547 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=4.465e+08
2023-07-07 06:35:18,846 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=4.506e+08
2023-07-07 06:35:45,094 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=4.547e+08
2023-07-07 06:36:11,350 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=4.588e+08
2023-07-07 06:36:37,514 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=4.629e+08
2023-07-07 06:37:03,822 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=4.670e+08
2023-07-07 06:37:30,266 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.711e+08
2023-07-07 06:37:56,470 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.752e+08
2023-07-07 06:38:22,619 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.793e+08
2023-07-07 06:38:48,779 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.834e+08
2023-07-07 06:39:15,095 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.875e+08
2023-07-07 06:39:41,176 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.915e+08
2023-07-07 06:39:41,177 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 06:39:41,203 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 06:39:41,203 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 06:39:41,235 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 06:39:45,264 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=4.137e+05
2023-07-07 06:39:48,211 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=8.233e+05
2023-07-07 06:39:51,110 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.233e+06
2023-07-07 06:39:54,016 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=1.642e+06
2023-07-07 06:39:56,934 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=2.052e+06
2023-07-07 06:39:59,873 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=2.462e+06
2023-07-07 06:40:02,767 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=2.871e+06
2023-07-07 06:40:05,667 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=3.281e+06
2023-07-07 06:40:08,592 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=3.690e+06
2023-07-07 06:40:11,498 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=4.100e+06
2023-07-07 06:40:14,366 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=4.510e+06
2023-07-07 06:40:17,268 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=4.919e+06
2023-07-07 06:40:20,167 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=5.329e+06
2023-07-07 06:40:23,078 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=5.738e+06
2023-07-07 06:40:25,985 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=6.148e+06
2023-07-07 06:40:28,864 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=6.558e+06
2023-07-07 06:40:31,746 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=6.967e+06
2023-07-07 06:40:34,627 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=7.377e+06
2023-07-07 06:40:37,496 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=7.786e+06
2023-07-07 06:40:40,365 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=8.196e+06
2023-07-07 06:40:43,234 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=8.606e+06
2023-07-07 06:40:46,121 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=9.015e+06
2023-07-07 06:40:49,004 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=9.425e+06
2023-07-07 06:40:51,883 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=9.834e+06
2023-07-07 06:40:54,765 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.024e+07
2023-07-07 06:40:57,651 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.065e+07
2023-07-07 06:41:00,547 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.106e+07
2023-07-07 06:41:03,437 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.147e+07
2023-07-07 06:41:06,327 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.188e+07
2023-07-07 06:41:09,208 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 06:41:12,096 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.270e+07
2023-07-07 06:41:14,984 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.311e+07
2023-07-07 06:41:17,870 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 06:41:20,759 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 06:41:23,664 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=1.434e+07
2023-07-07 06:41:26,582 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 06:41:29,494 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=1.516e+07
2023-07-07 06:41:32,414 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 06:41:35,321 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 06:41:38,212 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 06:41:41,102 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=1.680e+07
2023-07-07 06:41:43,985 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 06:41:46,869 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=1.762e+07
2023-07-07 06:41:49,750 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 06:41:52,663 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 06:41:55,573 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 06:41:58,470 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=1.926e+07
2023-07-07 06:42:01,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=1.966e+07
2023-07-07 06:42:04,277 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=2.007e+07
2023-07-07 06:42:07,191 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=2.048e+07
2023-07-07 06:42:10,105 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=2.089e+07
2023-07-07 06:42:13,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=2.130e+07
2023-07-07 06:42:15,935 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=2.171e+07
2023-07-07 06:42:18,847 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 06:42:21,758 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=2.253e+07
2023-07-07 06:42:24,666 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=2.294e+07
2023-07-07 06:42:27,590 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 06:42:30,480 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 06:42:33,370 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=2.417e+07
2023-07-07 06:42:36,260 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 06:42:39,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=2.499e+07
2023-07-07 06:42:42,068 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 06:42:44,961 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 06:42:47,866 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 06:42:50,771 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 06:42:53,676 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 06:42:56,589 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=2.745e+07
2023-07-07 06:42:59,485 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 06:43:02,397 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 06:43:05,275 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 06:43:08,158 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=2.909e+07
2023-07-07 06:43:11,038 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 06:43:13,913 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=2.990e+07
2023-07-07 06:43:16,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=3.031e+07
2023-07-07 06:43:19,672 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=3.072e+07
2023-07-07 06:43:22,541 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=3.113e+07
2023-07-07 06:43:25,426 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=3.154e+07
2023-07-07 06:43:28,324 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 06:43:31,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=3.236e+07
2023-07-07 06:43:34,140 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=3.277e+07
2023-07-07 06:43:37,040 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 06:43:39,935 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=3.359e+07
2023-07-07 06:43:42,826 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=3.400e+07
2023-07-07 06:43:45,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 06:43:48,605 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=3.482e+07
2023-07-07 06:43:51,493 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 06:43:54,380 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 06:43:57,264 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8800, best=0.71, avg=0.69, std=0.01, steps=3.605e+07
2023-07-07 06:44:00,149 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 8900, best=0.78, avg=0.76, std=0.01, steps=3.646e+07
2023-07-07 06:44:03,040 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9000, best=0.81, avg=0.80, std=0.01, steps=3.687e+07
2023-07-07 06:44:05,953 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=3.728e+07
2023-07-07 06:44:08,882 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9200, best=0.88, avg=0.86, std=0.01, steps=3.769e+07
2023-07-07 06:44:11,775 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9300, best=0.89, avg=0.87, std=0.01, steps=3.810e+07
2023-07-07 06:44:14,668 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9400, best=0.90, avg=0.89, std=0.00, steps=3.851e+07
2023-07-07 06:44:17,566 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9500, best=0.90, avg=0.90, std=0.00, steps=3.892e+07
2023-07-07 06:44:20,449 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9600, best=0.92, avg=0.91, std=0.00, steps=3.933e+07
2023-07-07 06:44:23,363 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9700, best=0.93, avg=0.92, std=0.00, steps=3.974e+07
2023-07-07 06:44:26,300 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9800, best=0.94, avg=0.93, std=0.00, steps=4.014e+07
2023-07-07 06:44:29,213 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 9900, best=0.94, avg=0.94, std=0.00, steps=4.055e+07
2023-07-07 06:44:32,123 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10000, best=0.95, avg=0.94, std=0.00, steps=4.096e+07
2023-07-07 06:44:35,034 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10100, best=0.95, avg=0.94, std=0.00, steps=4.137e+07
2023-07-07 06:44:37,960 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10200, best=0.95, avg=0.94, std=0.00, steps=4.178e+07
2023-07-07 06:44:40,872 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10300, best=0.95, avg=0.94, std=0.00, steps=4.219e+07
2023-07-07 06:44:43,777 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10400, best=0.95, avg=0.94, std=0.00, steps=4.260e+07
2023-07-07 06:44:46,669 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10500, best=0.95, avg=0.94, std=0.00, steps=4.301e+07
2023-07-07 06:44:49,582 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10600, best=0.95, avg=0.95, std=0.00, steps=4.342e+07
2023-07-07 06:44:52,504 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10700, best=0.95, avg=0.95, std=0.00, steps=4.383e+07
2023-07-07 06:44:55,381 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10800, best=0.95, avg=0.95, std=0.00, steps=4.424e+07
2023-07-07 06:44:58,274 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 10900, best=0.97, avg=0.96, std=0.00, steps=4.465e+07
2023-07-07 06:45:01,161 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11000, best=0.98, avg=0.97, std=0.00, steps=4.506e+07
2023-07-07 06:45:04,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11100, best=0.98, avg=0.98, std=0.00, steps=4.547e+07
2023-07-07 06:45:06,936 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11200, best=0.99, avg=0.99, std=0.00, steps=4.588e+07
2023-07-07 06:45:09,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11300, best=0.99, avg=0.99, std=0.00, steps=4.629e+07
2023-07-07 06:45:12,737 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11400, best=1.00, avg=1.00, std=0.00, steps=4.670e+07
2023-07-07 06:45:15,661 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11500, best=1.00, avg=1.00, std=0.00, steps=4.711e+07
2023-07-07 06:45:18,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11600, best=1.00, avg=1.00, std=0.00, steps=4.752e+07
2023-07-07 06:45:21,473 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11700, best=1.00, avg=1.00, std=0.00, steps=4.793e+07
2023-07-07 06:45:24,423 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11800, best=1.00, avg=1.00, std=0.00, steps=4.834e+07
2023-07-07 06:45:27,353 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11900, best=1.00, avg=1.00, std=0.00, steps=4.875e+07
2023-07-07 06:45:30,221 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 1, [Train]: 11999, best=1.00, avg=1.00, std=0.00, steps=4.915e+07
2023-07-07 06:45:30,221 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 06:45:30,247 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 06:45:30,247 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 06:45:30,280 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 06:45:35,908 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=6.205e+05
2023-07-07 06:45:40,137 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.235e+06
2023-07-07 06:45:44,390 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.849e+06
2023-07-07 06:45:48,607 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=2.464e+06
2023-07-07 06:45:52,789 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=3.078e+06
2023-07-07 06:45:56,963 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=3.693e+06
2023-07-07 06:46:01,151 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=4.307e+06
2023-07-07 06:46:05,362 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=4.921e+06
2023-07-07 06:46:09,555 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=5.536e+06
2023-07-07 06:46:13,747 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=6.150e+06
2023-07-07 06:46:17,921 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=6.765e+06
2023-07-07 06:46:22,130 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=7.379e+06
2023-07-07 06:46:26,343 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=7.993e+06
2023-07-07 06:46:30,567 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=8.608e+06
2023-07-07 06:46:34,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=9.222e+06
2023-07-07 06:46:39,021 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=9.837e+06
2023-07-07 06:46:43,239 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.045e+07
2023-07-07 06:46:47,449 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 06:46:51,639 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.168e+07
2023-07-07 06:46:55,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 06:47:00,033 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.291e+07
2023-07-07 06:47:04,260 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 06:47:08,492 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.414e+07
2023-07-07 06:47:12,720 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 06:47:16,920 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 06:47:21,104 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 06:47:25,291 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.659e+07
2023-07-07 06:47:29,478 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 06:47:33,713 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.782e+07
2023-07-07 06:47:37,951 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 06:47:42,208 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.905e+07
2023-07-07 06:47:46,424 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 06:47:50,681 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.028e+07
2023-07-07 06:47:54,878 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 06:47:59,066 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 06:48:03,270 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 06:48:07,504 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=2.274e+07
2023-07-07 06:48:11,718 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 06:48:15,932 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=2.397e+07
2023-07-07 06:48:20,149 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 06:48:24,360 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=2.520e+07
2023-07-07 06:48:28,547 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 06:48:32,729 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=2.643e+07
2023-07-07 06:48:36,914 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 06:48:41,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=2.765e+07
2023-07-07 06:48:45,365 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 06:48:49,590 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=2.888e+07
2023-07-07 06:48:53,798 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 06:48:58,019 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=3.011e+07
2023-07-07 06:49:02,206 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 06:49:06,397 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=3.134e+07
2023-07-07 06:49:10,591 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 06:49:14,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=3.257e+07
2023-07-07 06:49:18,964 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 06:49:23,152 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 06:49:27,335 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 06:49:31,505 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=3.503e+07
2023-07-07 06:49:35,690 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 06:49:39,861 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=3.626e+07
2023-07-07 06:49:44,092 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 06:49:48,322 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=3.748e+07
2023-07-07 06:49:52,552 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=3.810e+07
2023-07-07 06:49:56,785 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=3.871e+07
2023-07-07 06:50:00,962 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 06:50:05,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=3.994e+07
2023-07-07 06:50:09,330 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 06:50:13,506 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=4.117e+07
2023-07-07 06:50:17,695 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 06:50:21,876 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=4.240e+07
2023-07-07 06:50:26,065 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=4.301e+07
2023-07-07 06:50:30,248 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=4.363e+07
2023-07-07 06:50:34,432 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7200, best=0.66, avg=0.64, std=0.00, steps=4.424e+07
2023-07-07 06:50:38,637 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7300, best=0.72, avg=0.70, std=0.01, steps=4.486e+07
2023-07-07 06:50:42,859 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=4.547e+07
2023-07-07 06:50:47,071 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7500, best=0.74, avg=0.73, std=0.01, steps=4.609e+07
2023-07-07 06:50:51,280 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7600, best=0.74, avg=0.73, std=0.01, steps=4.670e+07
2023-07-07 06:50:55,493 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7700, best=0.75, avg=0.74, std=0.01, steps=4.731e+07
2023-07-07 06:50:59,734 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7800, best=0.77, avg=0.75, std=0.01, steps=4.793e+07
2023-07-07 06:51:04,002 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 7900, best=0.78, avg=0.76, std=0.01, steps=4.854e+07
2023-07-07 06:51:08,223 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8000, best=0.79, avg=0.77, std=0.01, steps=4.916e+07
2023-07-07 06:51:12,455 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8100, best=0.79, avg=0.77, std=0.01, steps=4.977e+07
2023-07-07 06:51:16,675 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8200, best=0.79, avg=0.78, std=0.01, steps=5.039e+07
2023-07-07 06:51:20,852 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8300, best=0.80, avg=0.79, std=0.01, steps=5.100e+07
2023-07-07 06:51:25,025 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8400, best=0.81, avg=0.79, std=0.01, steps=5.162e+07
2023-07-07 06:51:29,202 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8500, best=0.82, avg=0.80, std=0.01, steps=5.223e+07
2023-07-07 06:51:33,401 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8600, best=0.82, avg=0.81, std=0.01, steps=5.284e+07
2023-07-07 06:51:37,609 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8700, best=0.83, avg=0.81, std=0.01, steps=5.346e+07
2023-07-07 06:51:41,791 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8800, best=0.83, avg=0.81, std=0.00, steps=5.407e+07
2023-07-07 06:51:45,966 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 8900, best=0.83, avg=0.81, std=0.01, steps=5.469e+07
2023-07-07 06:51:50,139 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9000, best=0.84, avg=0.82, std=0.01, steps=5.530e+07
2023-07-07 06:51:54,330 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=5.592e+07
2023-07-07 06:51:58,500 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9200, best=0.85, avg=0.83, std=0.01, steps=5.653e+07
2023-07-07 06:52:02,692 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9300, best=0.85, avg=0.84, std=0.00, steps=5.715e+07
2023-07-07 06:52:06,866 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9400, best=0.86, avg=0.84, std=0.01, steps=5.776e+07
2023-07-07 06:52:11,036 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9500, best=0.85, avg=0.84, std=0.00, steps=5.837e+07
2023-07-07 06:52:15,228 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9600, best=0.86, avg=0.85, std=0.00, steps=5.899e+07
2023-07-07 06:52:19,406 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9700, best=0.86, avg=0.85, std=0.00, steps=5.960e+07
2023-07-07 06:52:23,577 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9800, best=0.87, avg=0.85, std=0.00, steps=6.022e+07
2023-07-07 06:52:27,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 9900, best=0.88, avg=0.86, std=0.00, steps=6.083e+07
2023-07-07 06:52:31,965 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10000, best=0.88, avg=0.86, std=0.00, steps=6.145e+07
2023-07-07 06:52:36,208 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10100, best=0.88, avg=0.87, std=0.00, steps=6.206e+07
2023-07-07 06:52:40,453 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10200, best=0.89, avg=0.88, std=0.00, steps=6.267e+07
2023-07-07 06:52:44,672 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10300, best=0.89, avg=0.88, std=0.00, steps=6.329e+07
2023-07-07 06:52:48,887 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10400, best=0.90, avg=0.89, std=0.00, steps=6.390e+07
2023-07-07 06:52:53,101 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10500, best=0.90, avg=0.88, std=0.00, steps=6.452e+07
2023-07-07 06:52:57,328 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10600, best=0.90, avg=0.89, std=0.00, steps=6.513e+07
2023-07-07 06:53:01,549 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10700, best=0.90, avg=0.89, std=0.00, steps=6.575e+07
2023-07-07 06:53:05,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10800, best=0.90, avg=0.89, std=0.00, steps=6.636e+07
2023-07-07 06:53:09,990 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 10900, best=0.90, avg=0.89, std=0.00, steps=6.698e+07
2023-07-07 06:53:14,218 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11000, best=0.91, avg=0.90, std=0.00, steps=6.759e+07
2023-07-07 06:53:18,439 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11100, best=0.91, avg=0.90, std=0.00, steps=6.820e+07
2023-07-07 06:53:22,622 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11200, best=0.91, avg=0.90, std=0.00, steps=6.882e+07
2023-07-07 06:53:26,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11300, best=0.91, avg=0.90, std=0.00, steps=6.943e+07
2023-07-07 06:53:31,022 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11400, best=0.91, avg=0.90, std=0.00, steps=7.005e+07
2023-07-07 06:53:35,253 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11500, best=0.91, avg=0.90, std=0.00, steps=7.066e+07
2023-07-07 06:53:39,486 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11600, best=0.92, avg=0.90, std=0.00, steps=7.128e+07
2023-07-07 06:53:43,707 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11700, best=0.92, avg=0.91, std=0.00, steps=7.189e+07
2023-07-07 06:53:47,929 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11800, best=0.92, avg=0.91, std=0.00, steps=7.251e+07
2023-07-07 06:53:52,227 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11900, best=0.92, avg=0.91, std=0.00, steps=7.312e+07
2023-07-07 06:53:56,420 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 1, [Train]: 11999, best=0.92, avg=0.91, std=0.00, steps=7.373e+07
2023-07-07 06:53:56,420 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 06:53:56,449 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 06:53:56,449 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 06:53:56,486 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 06:54:03,288 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 06:54:08,801 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 06:54:14,305 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 06:54:19,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 06:54:25,337 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 06:54:30,833 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 06:54:36,332 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 06:54:41,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 06:54:47,300 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 06:54:52,794 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 06:54:58,279 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=9.019e+06
2023-07-07 06:55:03,769 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 06:55:09,257 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 06:55:14,774 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 06:55:20,262 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 06:55:25,731 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 06:55:31,194 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 06:55:36,669 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 06:55:42,128 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 06:55:47,600 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 06:55:53,061 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 06:55:58,567 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 06:56:04,145 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 06:56:09,620 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 06:56:15,095 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 06:56:20,589 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 06:56:26,067 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 06:56:31,548 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 06:56:37,031 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 06:56:42,553 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 06:56:48,067 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 06:56:53,539 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 06:56:59,039 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 06:57:04,585 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 06:57:10,108 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 06:57:15,615 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 06:57:21,141 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 06:57:26,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 06:57:32,198 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 06:57:37,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 06:57:43,193 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 06:57:48,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 06:57:54,248 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 06:57:59,765 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 06:58:05,279 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 06:58:10,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 06:58:16,307 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 06:58:21,779 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 06:58:27,263 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 06:58:32,777 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 06:58:38,253 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 06:58:43,771 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 06:58:49,267 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 06:58:54,742 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 06:59:00,228 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 06:59:05,706 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 06:59:11,229 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 06:59:16,745 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 06:59:22,249 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 06:59:27,718 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 06:59:33,189 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 06:59:38,682 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 06:59:44,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 06:59:49,651 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 06:59:55,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 07:00:00,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 07:00:06,111 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 07:00:11,652 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 07:00:17,205 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 07:00:22,766 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 07:00:28,281 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 07:00:33,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 07:00:39,275 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7300, best=0.71, avg=0.69, std=0.01, steps=5.981e+07
2023-07-07 07:00:44,774 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=6.063e+07
2023-07-07 07:00:50,266 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7500, best=0.73, avg=0.71, std=0.01, steps=6.145e+07
2023-07-07 07:00:55,769 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7600, best=0.73, avg=0.72, std=0.01, steps=6.227e+07
2023-07-07 07:01:01,292 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7700, best=0.73, avg=0.72, std=0.01, steps=6.309e+07
2023-07-07 07:01:06,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7800, best=0.74, avg=0.73, std=0.01, steps=6.391e+07
2023-07-07 07:01:12,313 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 7900, best=0.75, avg=0.73, std=0.01, steps=6.472e+07
2023-07-07 07:01:17,788 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8000, best=0.75, avg=0.74, std=0.01, steps=6.554e+07
2023-07-07 07:01:23,258 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8100, best=0.76, avg=0.75, std=0.01, steps=6.636e+07
2023-07-07 07:01:28,709 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8200, best=0.77, avg=0.76, std=0.00, steps=6.718e+07
2023-07-07 07:01:34,206 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8300, best=0.78, avg=0.77, std=0.01, steps=6.800e+07
2023-07-07 07:01:39,723 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8400, best=0.79, avg=0.78, std=0.01, steps=6.882e+07
2023-07-07 07:01:45,260 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8500, best=0.80, avg=0.78, std=0.01, steps=6.964e+07
2023-07-07 07:01:50,752 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8600, best=0.81, avg=0.79, std=0.01, steps=7.046e+07
2023-07-07 07:01:56,236 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8700, best=0.80, avg=0.79, std=0.01, steps=7.128e+07
2023-07-07 07:02:01,710 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8800, best=0.81, avg=0.80, std=0.01, steps=7.210e+07
2023-07-07 07:02:07,186 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 8900, best=0.82, avg=0.80, std=0.01, steps=7.292e+07
2023-07-07 07:02:12,661 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9000, best=0.82, avg=0.80, std=0.01, steps=7.374e+07
2023-07-07 07:02:18,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9100, best=0.82, avg=0.81, std=0.01, steps=7.456e+07
2023-07-07 07:02:23,681 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9200, best=0.83, avg=0.81, std=0.01, steps=7.537e+07
2023-07-07 07:02:29,240 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9300, best=0.83, avg=0.81, std=0.01, steps=7.619e+07
2023-07-07 07:02:34,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9400, best=0.83, avg=0.82, std=0.01, steps=7.701e+07
2023-07-07 07:02:40,352 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9500, best=0.84, avg=0.82, std=0.01, steps=7.783e+07
2023-07-07 07:02:45,867 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9600, best=0.84, avg=0.83, std=0.01, steps=7.865e+07
2023-07-07 07:02:51,347 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9700, best=0.84, avg=0.83, std=0.00, steps=7.947e+07
2023-07-07 07:02:56,835 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9800, best=0.84, avg=0.83, std=0.00, steps=8.029e+07
2023-07-07 07:03:02,337 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 9900, best=0.85, avg=0.83, std=0.00, steps=8.111e+07
2023-07-07 07:03:07,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10000, best=0.85, avg=0.83, std=0.00, steps=8.193e+07
2023-07-07 07:03:13,294 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10100, best=0.85, avg=0.84, std=0.01, steps=8.275e+07
2023-07-07 07:03:18,774 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10200, best=0.85, avg=0.84, std=0.01, steps=8.357e+07
2023-07-07 07:03:24,290 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10300, best=0.85, avg=0.84, std=0.01, steps=8.439e+07
2023-07-07 07:03:29,772 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10400, best=0.85, avg=0.84, std=0.00, steps=8.520e+07
2023-07-07 07:03:35,281 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10500, best=0.85, avg=0.84, std=0.00, steps=8.602e+07
2023-07-07 07:03:40,800 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10600, best=0.86, avg=0.84, std=0.01, steps=8.684e+07
2023-07-07 07:03:46,272 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10700, best=0.86, avg=0.85, std=0.00, steps=8.766e+07
2023-07-07 07:03:51,787 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10800, best=0.86, avg=0.85, std=0.01, steps=8.848e+07
2023-07-07 07:03:57,297 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 10900, best=0.86, avg=0.85, std=0.00, steps=8.930e+07
2023-07-07 07:04:02,815 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11000, best=0.86, avg=0.85, std=0.00, steps=9.012e+07
2023-07-07 07:04:08,332 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11100, best=0.86, avg=0.85, std=0.00, steps=9.094e+07
2023-07-07 07:04:13,830 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11200, best=0.87, avg=0.85, std=0.00, steps=9.176e+07
2023-07-07 07:04:19,319 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11300, best=0.86, avg=0.86, std=0.00, steps=9.258e+07
2023-07-07 07:04:24,802 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11400, best=0.87, avg=0.86, std=0.00, steps=9.340e+07
2023-07-07 07:04:30,290 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11500, best=0.87, avg=0.86, std=0.00, steps=9.422e+07
2023-07-07 07:04:35,804 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11600, best=0.87, avg=0.86, std=0.00, steps=9.504e+07
2023-07-07 07:04:41,340 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11700, best=0.87, avg=0.86, std=0.00, steps=9.585e+07
2023-07-07 07:04:46,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11800, best=0.87, avg=0.86, std=0.00, steps=9.667e+07
2023-07-07 07:04:52,309 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11900, best=0.87, avg=0.86, std=0.00, steps=9.749e+07
2023-07-07 07:04:57,729 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 1, [Train]: 11999, best=0.87, avg=0.86, std=0.00, steps=9.830e+07
2023-07-07 07:04:57,729 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 07:04:57,755 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 07:04:57,755 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 07:04:57,789 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 07:05:07,217 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 07:05:15,305 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 07:05:23,377 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 07:05:31,509 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 07:05:39,586 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 07:05:47,715 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 07:05:55,815 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 07:06:03,948 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 07:06:12,062 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 07:06:20,111 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 07:06:28,165 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 07:06:36,222 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 07:06:44,343 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.599e+07
2023-07-07 07:06:52,455 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 07:07:00,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 07:07:08,685 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 07:07:16,837 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 07:07:24,940 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 07:07:33,003 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 07:07:41,072 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 07:07:49,135 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 07:07:57,198 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=2.705e+07
2023-07-07 07:08:05,288 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 07:08:13,366 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 07:08:21,452 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 07:08:29,585 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 07:08:37,656 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 07:08:45,757 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 07:08:53,877 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 07:09:01,940 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 07:09:10,024 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 07:09:18,150 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 07:09:26,259 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 07:09:34,334 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 07:09:42,455 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 07:09:50,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 07:09:58,600 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 07:10:06,694 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 07:10:14,728 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 07:10:22,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 07:10:30,844 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 07:10:38,984 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 07:10:47,049 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 07:10:55,102 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 07:11:03,147 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 07:11:11,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 07:11:19,368 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 07:11:27,461 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 07:11:35,517 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 07:11:43,568 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 07:11:51,692 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 07:11:59,775 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 07:12:07,866 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=6.514e+07
2023-07-07 07:12:15,995 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 07:12:24,059 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 07:12:32,192 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 07:12:40,329 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 07:12:48,470 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 07:12:56,598 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 07:13:04,727 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 07:13:12,857 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 07:13:21,005 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 07:13:29,098 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 07:13:37,163 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 07:13:45,249 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 07:13:53,362 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 07:14:01,412 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 07:14:09,507 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 07:14:17,613 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 07:14:25,678 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 07:14:33,732 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 07:14:41,826 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 07:14:49,896 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 07:14:57,936 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 07:15:06,010 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 07:15:14,122 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 07:15:22,209 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 07:15:30,266 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 07:15:38,316 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 07:15:46,376 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 07:15:54,438 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 07:16:02,500 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 07:16:10,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 07:16:18,647 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 07:16:26,712 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 07:16:34,774 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=1.057e+08
2023-07-07 07:16:42,836 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.069e+08
2023-07-07 07:16:50,905 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 07:16:58,984 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=1.094e+08
2023-07-07 07:17:07,071 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.106e+08
2023-07-07 07:17:15,129 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 07:17:23,171 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 07:17:31,225 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=1.143e+08
2023-07-07 07:17:39,273 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=1.155e+08
2023-07-07 07:17:47,341 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=1.167e+08
2023-07-07 07:17:55,458 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 07:18:03,514 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=1.192e+08
2023-07-07 07:18:11,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9800, best=0.53, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 07:18:19,633 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=1.217e+08
2023-07-07 07:18:27,688 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 07:18:35,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 07:18:43,918 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.253e+08
2023-07-07 07:18:51,978 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=1.266e+08
2023-07-07 07:19:00,039 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 07:19:08,097 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.290e+08
2023-07-07 07:19:16,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=1.303e+08
2023-07-07 07:19:24,219 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10700, best=0.65, avg=0.64, std=0.00, steps=1.315e+08
2023-07-07 07:19:32,289 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10800, best=0.65, avg=0.64, std=0.01, steps=1.327e+08
2023-07-07 07:19:40,402 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 10900, best=0.64, avg=0.63, std=0.01, steps=1.340e+08
2023-07-07 07:19:48,508 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11000, best=0.66, avg=0.65, std=0.01, steps=1.352e+08
2023-07-07 07:19:56,601 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11100, best=0.67, avg=0.66, std=0.00, steps=1.364e+08
2023-07-07 07:20:04,699 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11200, best=0.68, avg=0.67, std=0.01, steps=1.376e+08
2023-07-07 07:20:12,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11300, best=0.68, avg=0.67, std=0.01, steps=1.389e+08
2023-07-07 07:20:20,874 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11400, best=0.68, avg=0.67, std=0.01, steps=1.401e+08
2023-07-07 07:20:28,943 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11500, best=0.69, avg=0.67, std=0.01, steps=1.413e+08
2023-07-07 07:20:37,060 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11600, best=0.69, avg=0.67, std=0.01, steps=1.426e+08
2023-07-07 07:20:45,186 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11700, best=0.69, avg=0.68, std=0.01, steps=1.438e+08
2023-07-07 07:20:53,337 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11800, best=0.69, avg=0.68, std=0.01, steps=1.450e+08
2023-07-07 07:21:01,462 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11900, best=0.70, avg=0.68, std=0.01, steps=1.462e+08
2023-07-07 07:21:09,510 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 1, [Train]: 11999, best=0.71, avg=0.69, std=0.01, steps=1.475e+08
2023-07-07 07:21:09,510 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 07:21:09,535 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 07:21:09,536 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 07:21:09,569 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 07:21:16,311 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 07:21:21,822 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 07:21:27,295 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 07:21:32,788 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 07:21:38,307 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 07:21:43,820 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 07:21:49,331 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 07:21:54,837 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 07:22:00,351 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 07:22:05,853 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 07:22:11,362 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=9.019e+06
2023-07-07 07:22:16,870 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 07:22:22,376 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 07:22:27,897 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 07:22:33,393 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 07:22:38,843 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.312e+07
2023-07-07 07:22:44,292 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 07:22:49,741 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 07:22:55,217 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 07:23:00,713 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 07:23:06,212 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 07:23:11,673 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=1.803e+07
2023-07-07 07:23:17,142 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 07:23:22,636 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 07:23:28,088 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 07:23:33,537 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 07:23:39,015 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 07:23:44,530 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 07:23:50,045 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 07:23:55,557 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 07:24:01,070 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 07:24:06,589 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 07:24:12,072 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 07:24:17,531 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 07:24:23,015 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 07:24:28,531 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 07:24:34,017 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 07:24:39,504 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 07:24:44,982 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 07:24:50,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 07:24:55,930 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 07:25:01,403 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=3.441e+07
2023-07-07 07:25:06,868 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 07:25:12,329 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 07:25:17,778 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 07:25:23,271 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 07:25:28,768 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 07:25:34,271 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 07:25:39,758 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 07:25:45,223 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 07:25:50,726 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 07:25:56,228 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 07:26:01,725 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 07:26:07,231 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 07:26:12,741 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 07:26:18,250 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 07:26:23,754 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 07:26:29,270 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 07:26:34,786 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 07:26:40,297 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 07:26:45,787 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 07:26:51,265 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 07:26:56,749 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 07:27:02,195 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=5.244e+07
2023-07-07 07:27:07,679 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 07:27:13,189 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 07:27:18,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 07:27:24,167 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 07:27:29,627 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 07:27:35,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 07:27:40,549 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 07:27:46,010 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 07:27:51,523 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=5.981e+07
2023-07-07 07:27:57,072 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=6.063e+07
2023-07-07 07:28:02,605 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 07:28:08,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=6.227e+07
2023-07-07 07:28:13,639 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=6.309e+07
2023-07-07 07:28:19,155 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 07:28:24,636 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=6.472e+07
2023-07-07 07:28:30,082 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=6.554e+07
2023-07-07 07:28:35,529 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8100, best=0.68, avg=0.67, std=0.00, steps=6.636e+07
2023-07-07 07:28:40,999 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8200, best=0.71, avg=0.70, std=0.00, steps=6.718e+07
2023-07-07 07:28:46,458 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8300, best=0.73, avg=0.72, std=0.00, steps=6.800e+07
2023-07-07 07:28:51,947 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8400, best=0.75, avg=0.74, std=0.00, steps=6.882e+07
2023-07-07 07:28:57,460 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8500, best=0.76, avg=0.75, std=0.00, steps=6.964e+07
2023-07-07 07:29:02,954 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8600, best=0.77, avg=0.76, std=0.00, steps=7.046e+07
2023-07-07 07:29:08,446 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8700, best=0.77, avg=0.76, std=0.00, steps=7.128e+07
2023-07-07 07:29:13,942 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8800, best=0.78, avg=0.77, std=0.00, steps=7.210e+07
2023-07-07 07:29:19,445 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 8900, best=0.79, avg=0.78, std=0.00, steps=7.292e+07
2023-07-07 07:29:24,940 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9000, best=0.80, avg=0.79, std=0.00, steps=7.374e+07
2023-07-07 07:29:30,417 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9100, best=0.81, avg=0.80, std=0.00, steps=7.456e+07
2023-07-07 07:29:35,865 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9200, best=0.81, avg=0.80, std=0.00, steps=7.537e+07
2023-07-07 07:29:41,319 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9300, best=0.82, avg=0.81, std=0.00, steps=7.619e+07
2023-07-07 07:29:46,799 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9400, best=0.83, avg=0.82, std=0.00, steps=7.701e+07
2023-07-07 07:29:52,310 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9500, best=0.83, avg=0.82, std=0.00, steps=7.783e+07
2023-07-07 07:29:57,782 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9600, best=0.84, avg=0.83, std=0.00, steps=7.865e+07
2023-07-07 07:30:03,272 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9700, best=0.85, avg=0.84, std=0.00, steps=7.947e+07
2023-07-07 07:30:08,756 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9800, best=0.85, avg=0.84, std=0.00, steps=8.029e+07
2023-07-07 07:30:14,235 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 9900, best=0.85, avg=0.85, std=0.00, steps=8.111e+07
2023-07-07 07:30:19,712 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10000, best=0.86, avg=0.85, std=0.00, steps=8.193e+07
2023-07-07 07:30:25,192 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10100, best=0.86, avg=0.86, std=0.00, steps=8.275e+07
2023-07-07 07:30:30,654 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10200, best=0.87, avg=0.86, std=0.00, steps=8.357e+07
2023-07-07 07:30:36,122 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10300, best=0.87, avg=0.86, std=0.00, steps=8.439e+07
2023-07-07 07:30:41,595 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10400, best=0.88, avg=0.87, std=0.00, steps=8.520e+07
2023-07-07 07:30:47,070 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10500, best=0.88, avg=0.87, std=0.00, steps=8.602e+07
2023-07-07 07:30:52,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10600, best=0.88, avg=0.87, std=0.00, steps=8.684e+07
2023-07-07 07:30:58,063 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10700, best=0.89, avg=0.88, std=0.00, steps=8.766e+07
2023-07-07 07:31:03,539 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10800, best=0.89, avg=0.88, std=0.00, steps=8.848e+07
2023-07-07 07:31:09,018 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 10900, best=0.89, avg=0.88, std=0.00, steps=8.930e+07
2023-07-07 07:31:14,479 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11000, best=0.89, avg=0.88, std=0.00, steps=9.012e+07
2023-07-07 07:31:19,952 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11100, best=0.89, avg=0.88, std=0.00, steps=9.094e+07
2023-07-07 07:31:25,403 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11200, best=0.89, avg=0.89, std=0.00, steps=9.176e+07
2023-07-07 07:31:30,853 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11300, best=0.90, avg=0.89, std=0.00, steps=9.258e+07
2023-07-07 07:31:36,298 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11400, best=0.89, avg=0.89, std=0.00, steps=9.340e+07
2023-07-07 07:31:41,743 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11500, best=0.90, avg=0.89, std=0.00, steps=9.422e+07
2023-07-07 07:31:47,186 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11600, best=0.90, avg=0.89, std=0.00, steps=9.504e+07
2023-07-07 07:31:52,639 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11700, best=0.90, avg=0.89, std=0.00, steps=9.585e+07
2023-07-07 07:31:58,115 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11800, best=0.90, avg=0.89, std=0.00, steps=9.667e+07
2023-07-07 07:32:03,588 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11900, best=0.90, avg=0.89, std=0.00, steps=9.749e+07
2023-07-07 07:32:09,034 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 1, [Train]: 11999, best=0.90, avg=0.89, std=0.00, steps=9.830e+07
2023-07-07 07:32:09,035 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 07:32:09,059 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 07:32:09,059 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 07:32:09,092 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 07:32:17,241 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.034e+06
2023-07-07 07:32:24,223 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=2.058e+06
2023-07-07 07:32:30,993 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.082e+06
2023-07-07 07:32:37,808 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.106e+06
2023-07-07 07:32:44,640 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=5.130e+06
2023-07-07 07:32:51,462 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=6.154e+06
2023-07-07 07:32:58,275 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=7.178e+06
2023-07-07 07:33:05,083 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=8.202e+06
2023-07-07 07:33:11,884 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=9.226e+06
2023-07-07 07:33:18,672 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.025e+07
2023-07-07 07:33:25,511 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.127e+07
2023-07-07 07:33:32,320 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 07:33:39,088 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.332e+07
2023-07-07 07:33:45,852 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.435e+07
2023-07-07 07:33:52,605 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 07:33:59,355 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.639e+07
2023-07-07 07:34:06,110 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=1.742e+07
2023-07-07 07:34:12,874 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 07:34:19,605 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.947e+07
2023-07-07 07:34:26,366 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 07:34:33,117 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 07:34:39,862 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=2.254e+07
2023-07-07 07:34:46,627 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.356e+07
2023-07-07 07:34:53,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 07:35:00,271 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=2.561e+07
2023-07-07 07:35:07,041 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 07:35:13,821 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.766e+07
2023-07-07 07:35:20,591 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 07:35:27,350 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=2.971e+07
2023-07-07 07:35:34,110 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 07:35:40,878 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=3.175e+07
2023-07-07 07:35:47,638 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 07:35:54,401 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 07:36:01,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=3.483e+07
2023-07-07 07:36:07,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=3.585e+07
2023-07-07 07:36:14,688 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 07:36:21,447 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.790e+07
2023-07-07 07:36:28,209 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=3.892e+07
2023-07-07 07:36:34,962 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=3.995e+07
2023-07-07 07:36:41,721 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 07:36:48,475 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=4.199e+07
2023-07-07 07:36:55,258 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=4.302e+07
2023-07-07 07:37:02,043 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=4.404e+07
2023-07-07 07:37:08,809 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=4.507e+07
2023-07-07 07:37:15,578 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=4.609e+07
2023-07-07 07:37:22,348 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=4.711e+07
2023-07-07 07:37:29,100 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=4.814e+07
2023-07-07 07:37:35,855 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 07:37:42,618 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=5.019e+07
2023-07-07 07:37:49,411 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=5.121e+07
2023-07-07 07:37:56,241 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=5.223e+07
2023-07-07 07:38:03,075 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 07:38:09,911 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=5.428e+07
2023-07-07 07:38:16,738 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 07:38:23,574 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=5.633e+07
2023-07-07 07:38:30,406 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 07:38:37,252 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=5.838e+07
2023-07-07 07:38:44,067 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=5.940e+07
2023-07-07 07:38:50,864 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=6.043e+07
2023-07-07 07:38:57,640 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 07:39:04,403 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=6.247e+07
2023-07-07 07:39:11,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=6.350e+07
2023-07-07 07:39:17,932 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=6.452e+07
2023-07-07 07:39:24,687 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=6.555e+07
2023-07-07 07:39:31,462 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=6.657e+07
2023-07-07 07:39:38,290 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=6.759e+07
2023-07-07 07:39:45,068 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=6.862e+07
2023-07-07 07:39:51,851 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=6.964e+07
2023-07-07 07:39:58,624 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=7.067e+07
2023-07-07 07:40:05,387 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=7.169e+07
2023-07-07 07:40:12,154 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=7.271e+07
2023-07-07 07:40:18,936 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 07:40:25,740 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=7.476e+07
2023-07-07 07:40:32,545 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=7.579e+07
2023-07-07 07:40:39,344 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=7.681e+07
2023-07-07 07:40:46,153 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=7.783e+07
2023-07-07 07:40:52,975 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=7.886e+07
2023-07-07 07:40:59,841 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7800, best=0.65, avg=0.64, std=0.00, steps=7.988e+07
2023-07-07 07:41:06,660 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 7900, best=0.68, avg=0.67, std=0.00, steps=8.091e+07
2023-07-07 07:41:13,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8000, best=0.70, avg=0.69, std=0.00, steps=8.193e+07
2023-07-07 07:41:20,287 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8100, best=0.71, avg=0.70, std=0.00, steps=8.295e+07
2023-07-07 07:41:27,117 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8200, best=0.71, avg=0.70, std=0.00, steps=8.398e+07
2023-07-07 07:41:33,939 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8300, best=0.72, avg=0.71, std=0.00, steps=8.500e+07
2023-07-07 07:41:40,767 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8400, best=0.73, avg=0.71, std=0.00, steps=8.603e+07
2023-07-07 07:41:47,555 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8500, best=0.73, avg=0.72, std=0.00, steps=8.705e+07
2023-07-07 07:41:54,322 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8600, best=0.73, avg=0.72, std=0.00, steps=8.807e+07
2023-07-07 07:42:01,097 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8700, best=0.74, avg=0.73, std=0.00, steps=8.910e+07
2023-07-07 07:42:07,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8800, best=0.74, avg=0.73, std=0.00, steps=9.012e+07
2023-07-07 07:42:14,764 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 8900, best=0.75, avg=0.74, std=0.00, steps=9.115e+07
2023-07-07 07:42:21,593 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9000, best=0.76, avg=0.75, std=0.00, steps=9.217e+07
2023-07-07 07:42:28,421 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9100, best=0.76, avg=0.75, std=0.00, steps=9.319e+07
2023-07-07 07:42:35,254 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9200, best=0.76, avg=0.75, std=0.00, steps=9.422e+07
2023-07-07 07:42:42,053 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9300, best=0.77, avg=0.76, std=0.00, steps=9.524e+07
2023-07-07 07:42:48,800 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9400, best=0.77, avg=0.76, std=0.00, steps=9.627e+07
2023-07-07 07:42:55,557 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9500, best=0.78, avg=0.77, std=0.00, steps=9.729e+07
2023-07-07 07:43:02,326 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9600, best=0.78, avg=0.77, std=0.00, steps=9.831e+07
2023-07-07 07:43:09,107 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9700, best=0.79, avg=0.77, std=0.00, steps=9.934e+07
2023-07-07 07:43:15,913 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9800, best=0.79, avg=0.78, std=0.00, steps=1.004e+08
2023-07-07 07:43:22,758 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 9900, best=0.79, avg=0.78, std=0.00, steps=1.014e+08
2023-07-07 07:43:29,600 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10000, best=0.79, avg=0.78, std=0.00, steps=1.024e+08
2023-07-07 07:43:36,378 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10100, best=0.79, avg=0.79, std=0.00, steps=1.034e+08
2023-07-07 07:43:43,194 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10200, best=0.80, avg=0.79, std=0.00, steps=1.045e+08
2023-07-07 07:43:49,964 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10300, best=0.80, avg=0.79, std=0.00, steps=1.055e+08
2023-07-07 07:43:56,720 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10400, best=0.80, avg=0.79, std=0.00, steps=1.065e+08
2023-07-07 07:44:03,470 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10500, best=0.81, avg=0.79, std=0.00, steps=1.075e+08
2023-07-07 07:44:10,285 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10600, best=0.80, avg=0.80, std=0.00, steps=1.086e+08
2023-07-07 07:44:17,037 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10700, best=0.80, avg=0.80, std=0.00, steps=1.096e+08
2023-07-07 07:44:23,786 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10800, best=0.81, avg=0.80, std=0.00, steps=1.106e+08
2023-07-07 07:44:30,581 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 10900, best=0.81, avg=0.80, std=0.00, steps=1.116e+08
2023-07-07 07:44:37,410 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11000, best=0.81, avg=0.80, std=0.00, steps=1.127e+08
2023-07-07 07:44:44,289 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11100, best=0.82, avg=0.81, std=0.00, steps=1.137e+08
2023-07-07 07:44:51,108 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11200, best=0.82, avg=0.81, std=0.00, steps=1.147e+08
2023-07-07 07:44:57,874 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11300, best=0.82, avg=0.81, std=0.00, steps=1.157e+08
2023-07-07 07:45:04,646 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11400, best=0.82, avg=0.81, std=0.00, steps=1.167e+08
2023-07-07 07:45:11,417 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11500, best=0.82, avg=0.81, std=0.00, steps=1.178e+08
2023-07-07 07:45:18,206 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11600, best=0.82, avg=0.81, std=0.00, steps=1.188e+08
2023-07-07 07:45:25,018 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11700, best=0.83, avg=0.82, std=0.00, steps=1.198e+08
2023-07-07 07:45:31,819 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11800, best=0.83, avg=0.82, std=0.00, steps=1.208e+08
2023-07-07 07:45:38,634 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11900, best=0.83, avg=0.82, std=0.00, steps=1.219e+08
2023-07-07 07:45:45,394 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 1, [Train]: 11999, best=0.83, avg=0.82, std=0.00, steps=1.229e+08
2023-07-07 07:45:45,394 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 07:45:45,420 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 07:45:45,420 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 07:45:45,453 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 07:45:54,836 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 07:46:02,976 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 07:46:11,143 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 07:46:19,206 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 07:46:27,274 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 07:46:35,407 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 07:46:43,508 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 07:46:51,601 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 07:46:59,778 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 07:47:07,918 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 07:47:16,028 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 07:47:24,069 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 07:47:32,090 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.599e+07
2023-07-07 07:47:40,147 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 07:47:48,231 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 07:47:56,381 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.967e+07
2023-07-07 07:48:04,540 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 07:48:12,671 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 07:48:20,808 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 07:48:28,930 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 07:48:36,967 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 07:48:45,006 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=2.705e+07
2023-07-07 07:48:53,036 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 07:49:01,075 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 07:49:09,143 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 07:49:17,207 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 07:49:25,324 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 07:49:33,456 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 07:49:41,550 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 07:49:49,588 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 07:49:57,707 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 07:50:05,826 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 07:50:13,976 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 07:50:22,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 07:50:30,195 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 07:50:38,313 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 07:50:46,416 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 07:50:54,524 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 07:51:02,626 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 07:51:10,708 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 07:51:18,757 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 07:51:26,796 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=5.162e+07
2023-07-07 07:51:34,915 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 07:51:43,061 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 07:51:51,154 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 07:51:59,278 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 07:52:07,378 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 07:52:15,443 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 07:52:23,525 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 07:52:31,590 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 07:52:39,614 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 07:52:47,647 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 07:52:55,704 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=6.514e+07
2023-07-07 07:53:03,757 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 07:53:11,810 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 07:53:19,977 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 07:53:28,147 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 07:53:36,202 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 07:53:44,233 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 07:53:52,260 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 07:54:00,316 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 07:54:08,437 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 07:54:16,561 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 07:54:24,622 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=7.866e+07
2023-07-07 07:54:32,664 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 07:54:40,712 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 07:54:48,753 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 07:54:56,815 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 07:55:04,864 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 07:55:12,920 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 07:55:21,037 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 07:55:29,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 07:55:37,288 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 07:55:45,392 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 07:55:53,516 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 07:56:01,638 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 07:56:09,756 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 07:56:17,879 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 07:56:26,002 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 07:56:34,091 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 07:56:42,189 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 07:56:50,303 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 07:56:58,418 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 07:57:06,484 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 07:57:14,587 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 07:57:22,632 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8600, best=0.59, avg=0.58, std=0.00, steps=1.057e+08
2023-07-07 07:57:30,688 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8700, best=0.65, avg=0.64, std=0.00, steps=1.069e+08
2023-07-07 07:57:38,762 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8800, best=0.67, avg=0.66, std=0.00, steps=1.081e+08
2023-07-07 07:57:46,879 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 8900, best=0.69, avg=0.68, std=0.00, steps=1.094e+08
2023-07-07 07:57:55,011 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9000, best=0.70, avg=0.69, std=0.00, steps=1.106e+08
2023-07-07 07:58:03,137 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9100, best=0.71, avg=0.70, std=0.00, steps=1.118e+08
2023-07-07 07:58:11,288 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9200, best=0.71, avg=0.70, std=0.00, steps=1.131e+08
2023-07-07 07:58:19,402 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9300, best=0.72, avg=0.70, std=0.00, steps=1.143e+08
2023-07-07 07:58:27,533 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9400, best=0.72, avg=0.71, std=0.00, steps=1.155e+08
2023-07-07 07:58:35,672 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9500, best=0.72, avg=0.71, std=0.00, steps=1.167e+08
2023-07-07 07:58:43,809 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9600, best=0.72, avg=0.71, std=0.00, steps=1.180e+08
2023-07-07 07:58:51,931 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9700, best=0.73, avg=0.72, std=0.00, steps=1.192e+08
2023-07-07 07:59:00,043 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9800, best=0.73, avg=0.72, std=0.00, steps=1.204e+08
2023-07-07 07:59:08,162 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 9900, best=0.73, avg=0.72, std=0.00, steps=1.217e+08
2023-07-07 07:59:16,274 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10000, best=0.74, avg=0.73, std=0.00, steps=1.229e+08
2023-07-07 07:59:24,373 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10100, best=0.74, avg=0.73, std=0.00, steps=1.241e+08
2023-07-07 07:59:32,473 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10200, best=0.74, avg=0.73, std=0.00, steps=1.253e+08
2023-07-07 07:59:40,582 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10300, best=0.75, avg=0.73, std=0.00, steps=1.266e+08
2023-07-07 07:59:48,788 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10400, best=0.75, avg=0.74, std=0.00, steps=1.278e+08
2023-07-07 07:59:56,888 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10500, best=0.75, avg=0.74, std=0.00, steps=1.290e+08
2023-07-07 08:00:04,931 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10600, best=0.75, avg=0.74, std=0.00, steps=1.303e+08
2023-07-07 08:00:12,992 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10700, best=0.75, avg=0.74, std=0.00, steps=1.315e+08
2023-07-07 08:00:21,087 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10800, best=0.75, avg=0.74, std=0.00, steps=1.327e+08
2023-07-07 08:00:29,133 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 10900, best=0.75, avg=0.74, std=0.00, steps=1.340e+08
2023-07-07 08:00:37,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11000, best=0.76, avg=0.75, std=0.00, steps=1.352e+08
2023-07-07 08:00:45,238 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11100, best=0.76, avg=0.75, std=0.00, steps=1.364e+08
2023-07-07 08:00:53,290 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11200, best=0.76, avg=0.75, std=0.00, steps=1.376e+08
2023-07-07 08:01:01,391 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11300, best=0.76, avg=0.75, std=0.00, steps=1.389e+08
2023-07-07 08:01:09,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11400, best=0.76, avg=0.75, std=0.00, steps=1.401e+08
2023-07-07 08:01:17,497 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11500, best=0.76, avg=0.75, std=0.00, steps=1.413e+08
2023-07-07 08:01:25,533 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11600, best=0.76, avg=0.75, std=0.00, steps=1.426e+08
2023-07-07 08:01:33,592 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11700, best=0.77, avg=0.76, std=0.00, steps=1.438e+08
2023-07-07 08:01:41,632 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11800, best=0.77, avg=0.76, std=0.00, steps=1.450e+08
2023-07-07 08:01:49,671 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11900, best=0.77, avg=0.76, std=0.00, steps=1.462e+08
2023-07-07 08:01:57,625 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 1, [Train]: 11999, best=0.77, avg=0.76, std=0.00, steps=1.475e+08
2023-07-07 08:01:57,626 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 08:01:57,651 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 08:01:57,651 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 08:01:57,683 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 08:02:09,667 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.655e+06
2023-07-07 08:02:20,377 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=3.293e+06
2023-07-07 08:02:31,029 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=4.932e+06
2023-07-07 08:02:41,634 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=6.570e+06
2023-07-07 08:02:52,256 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=8.208e+06
2023-07-07 08:03:02,905 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=9.847e+06
2023-07-07 08:03:13,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=1.149e+07
2023-07-07 08:03:24,280 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 08:03:35,034 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 08:03:45,783 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.640e+07
2023-07-07 08:03:56,623 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.804e+07
2023-07-07 08:04:07,394 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.968e+07
2023-07-07 08:04:18,132 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=2.132e+07
2023-07-07 08:04:28,847 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 08:04:39,566 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 08:04:50,272 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 08:05:00,977 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=2.787e+07
2023-07-07 08:05:11,608 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.951e+07
2023-07-07 08:05:22,246 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=3.115e+07
2023-07-07 08:05:32,896 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 08:05:43,552 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 08:05:54,247 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=3.606e+07
2023-07-07 08:06:04,931 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=3.770e+07
2023-07-07 08:06:15,668 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=3.934e+07
2023-07-07 08:06:26,438 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=4.098e+07
2023-07-07 08:06:37,142 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 08:06:47,784 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 08:06:58,408 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=4.589e+07
2023-07-07 08:07:09,055 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=4.753e+07
2023-07-07 08:07:19,670 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=4.917e+07
2023-07-07 08:07:30,291 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=5.081e+07
2023-07-07 08:07:40,903 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=5.245e+07
2023-07-07 08:07:51,539 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 08:08:02,167 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=5.572e+07
2023-07-07 08:08:12,838 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=5.736e+07
2023-07-07 08:08:23,513 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=5.900e+07
2023-07-07 08:08:34,156 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=6.064e+07
2023-07-07 08:08:44,804 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=6.228e+07
2023-07-07 08:08:55,449 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 08:09:06,125 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=6.555e+07
2023-07-07 08:09:16,776 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=6.719e+07
2023-07-07 08:09:27,419 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=6.883e+07
2023-07-07 08:09:38,073 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=7.047e+07
2023-07-07 08:09:48,723 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=7.211e+07
2023-07-07 08:09:59,369 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 08:10:10,014 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=7.538e+07
2023-07-07 08:10:20,759 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=7.702e+07
2023-07-07 08:10:31,406 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 08:10:42,054 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=8.030e+07
2023-07-07 08:10:52,697 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=8.194e+07
2023-07-07 08:11:03,343 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 08:11:13,983 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=8.521e+07
2023-07-07 08:11:24,647 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=8.685e+07
2023-07-07 08:11:35,312 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 08:11:45,965 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=9.013e+07
2023-07-07 08:11:56,613 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=9.177e+07
2023-07-07 08:12:07,267 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=9.341e+07
2023-07-07 08:12:17,909 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=9.504e+07
2023-07-07 08:12:28,670 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=9.668e+07
2023-07-07 08:12:39,293 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 08:12:49,931 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=9.996e+07
2023-07-07 08:13:00,579 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=1.016e+08
2023-07-07 08:13:11,242 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 08:13:21,873 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 08:13:32,499 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=1.065e+08
2023-07-07 08:13:43,194 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=1.082e+08
2023-07-07 08:13:53,895 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=1.098e+08
2023-07-07 08:14:04,616 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=1.114e+08
2023-07-07 08:14:15,337 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 08:14:26,056 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=1.147e+08
2023-07-07 08:14:36,775 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=1.163e+08
2023-07-07 08:14:47,544 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 08:14:58,250 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=1.196e+08
2023-07-07 08:15:08,954 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=1.213e+08
2023-07-07 08:15:19,644 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 08:15:30,395 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=1.245e+08
2023-07-07 08:15:41,100 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=1.262e+08
2023-07-07 08:15:51,763 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 08:16:02,475 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=1.294e+08
2023-07-07 08:16:13,155 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=1.311e+08
2023-07-07 08:16:23,876 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=1.327e+08
2023-07-07 08:16:34,649 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.344e+08
2023-07-07 08:16:45,396 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.01, steps=1.360e+08
2023-07-07 08:16:56,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.376e+08
2023-07-07 08:17:06,807 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.01, steps=1.393e+08
2023-07-07 08:17:17,507 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.01, steps=1.409e+08
2023-07-07 08:17:28,183 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.01, steps=1.426e+08
2023-07-07 08:17:38,969 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.01, steps=1.442e+08
2023-07-07 08:17:49,760 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.01, steps=1.458e+08
2023-07-07 08:18:00,501 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.475e+08
2023-07-07 08:18:11,259 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9100, best=0.61, avg=0.60, std=0.00, steps=1.491e+08
2023-07-07 08:18:21,918 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9200, best=0.66, avg=0.64, std=0.00, steps=1.507e+08
2023-07-07 08:18:32,574 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9300, best=0.66, avg=0.65, std=0.00, steps=1.524e+08
2023-07-07 08:18:43,242 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9400, best=0.66, avg=0.65, std=0.00, steps=1.540e+08
2023-07-07 08:18:53,936 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9500, best=0.67, avg=0.66, std=0.00, steps=1.557e+08
2023-07-07 08:19:04,624 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9600, best=0.67, avg=0.66, std=0.00, steps=1.573e+08
2023-07-07 08:19:15,334 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9700, best=0.68, avg=0.67, std=0.00, steps=1.589e+08
2023-07-07 08:19:26,096 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9800, best=0.68, avg=0.67, std=0.00, steps=1.606e+08
2023-07-07 08:19:36,764 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 9900, best=0.68, avg=0.67, std=0.00, steps=1.622e+08
2023-07-07 08:19:47,451 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10000, best=0.69, avg=0.68, std=0.00, steps=1.639e+08
2023-07-07 08:19:58,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10100, best=0.69, avg=0.68, std=0.00, steps=1.655e+08
2023-07-07 08:20:08,906 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10200, best=0.69, avg=0.68, std=0.00, steps=1.671e+08
2023-07-07 08:20:19,640 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10300, best=0.69, avg=0.68, std=0.00, steps=1.688e+08
2023-07-07 08:20:30,345 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10400, best=0.70, avg=0.69, std=0.00, steps=1.704e+08
2023-07-07 08:20:41,072 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10500, best=0.70, avg=0.69, std=0.00, steps=1.720e+08
2023-07-07 08:20:51,842 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10600, best=0.70, avg=0.69, std=0.00, steps=1.737e+08
2023-07-07 08:21:02,600 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10700, best=0.70, avg=0.69, std=0.00, steps=1.753e+08
2023-07-07 08:21:13,355 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10800, best=0.71, avg=0.69, std=0.00, steps=1.770e+08
2023-07-07 08:21:24,068 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 10900, best=0.70, avg=0.70, std=0.00, steps=1.786e+08
2023-07-07 08:21:34,725 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11000, best=0.71, avg=0.70, std=0.00, steps=1.802e+08
2023-07-07 08:21:45,420 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11100, best=0.71, avg=0.70, std=0.00, steps=1.819e+08
2023-07-07 08:21:56,110 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11200, best=0.71, avg=0.70, std=0.00, steps=1.835e+08
2023-07-07 08:22:06,800 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11300, best=0.71, avg=0.70, std=0.00, steps=1.852e+08
2023-07-07 08:22:17,491 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11400, best=0.71, avg=0.70, std=0.00, steps=1.868e+08
2023-07-07 08:22:28,183 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11500, best=0.71, avg=0.70, std=0.00, steps=1.884e+08
2023-07-07 08:22:38,924 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11600, best=0.71, avg=0.70, std=0.00, steps=1.901e+08
2023-07-07 08:22:49,670 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11700, best=0.71, avg=0.70, std=0.00, steps=1.917e+08
2023-07-07 08:23:00,397 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11800, best=0.72, avg=0.71, std=0.00, steps=1.933e+08
2023-07-07 08:23:11,200 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11900, best=0.72, avg=0.71, std=0.00, steps=1.950e+08
2023-07-07 08:23:21,868 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 1, [Train]: 11999, best=0.71, avg=0.71, std=0.00, steps=1.966e+08
2023-07-07 08:23:21,869 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 08:23:21,894 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 08:23:21,894 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 08:23:21,928 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 08:23:34,021 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=1.655e+06
2023-07-07 08:23:44,794 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=3.293e+06
2023-07-07 08:23:55,551 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=4.932e+06
2023-07-07 08:24:06,325 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=6.570e+06
2023-07-07 08:24:17,105 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=8.208e+06
2023-07-07 08:24:27,861 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=9.847e+06
2023-07-07 08:24:38,630 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.149e+07
2023-07-07 08:24:49,371 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.312e+07
2023-07-07 08:25:00,020 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.476e+07
2023-07-07 08:25:10,712 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=1.640e+07
2023-07-07 08:25:21,497 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=1.804e+07
2023-07-07 08:25:32,255 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=1.968e+07
2023-07-07 08:25:43,024 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.132e+07
2023-07-07 08:25:53,734 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.295e+07
2023-07-07 08:26:04,476 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=2.459e+07
2023-07-07 08:26:15,167 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 08:26:25,866 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=2.787e+07
2023-07-07 08:26:36,648 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=2.951e+07
2023-07-07 08:26:47,421 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.115e+07
2023-07-07 08:26:58,190 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=3.278e+07
2023-07-07 08:27:08,938 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=3.442e+07
2023-07-07 08:27:19,620 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=3.606e+07
2023-07-07 08:27:30,379 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=3.770e+07
2023-07-07 08:27:41,120 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=3.934e+07
2023-07-07 08:27:51,852 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=4.098e+07
2023-07-07 08:28:02,574 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=4.261e+07
2023-07-07 08:28:13,332 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=4.425e+07
2023-07-07 08:28:24,005 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=4.589e+07
2023-07-07 08:28:34,662 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=4.753e+07
2023-07-07 08:28:45,360 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=4.917e+07
2023-07-07 08:28:56,081 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=5.081e+07
2023-07-07 08:29:06,800 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=5.245e+07
2023-07-07 08:29:17,512 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=5.408e+07
2023-07-07 08:29:28,225 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=5.572e+07
2023-07-07 08:29:38,921 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=5.736e+07
2023-07-07 08:29:49,620 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=5.900e+07
2023-07-07 08:30:00,340 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=6.064e+07
2023-07-07 08:30:11,082 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=6.228e+07
2023-07-07 08:30:21,804 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=6.391e+07
2023-07-07 08:30:32,537 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=6.555e+07
2023-07-07 08:30:43,259 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=6.719e+07
2023-07-07 08:30:53,973 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4200, best=0.52, avg=0.50, std=0.00, steps=6.883e+07
2023-07-07 08:31:04,683 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=7.047e+07
2023-07-07 08:31:15,363 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=7.211e+07
2023-07-07 08:31:26,065 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=7.374e+07
2023-07-07 08:31:36,733 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4600, best=0.52, avg=0.50, std=0.00, steps=7.538e+07
2023-07-07 08:31:47,476 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=7.702e+07
2023-07-07 08:31:58,164 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4800, best=0.52, avg=0.50, std=0.00, steps=7.866e+07
2023-07-07 08:32:08,899 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=8.030e+07
2023-07-07 08:32:19,630 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=8.194e+07
2023-07-07 08:32:30,380 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=8.357e+07
2023-07-07 08:32:41,095 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=8.521e+07
2023-07-07 08:32:51,828 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=8.685e+07
2023-07-07 08:33:02,519 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5400, best=0.52, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 08:33:13,233 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 08:33:23,978 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=9.177e+07
2023-07-07 08:33:34,712 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=9.341e+07
2023-07-07 08:33:45,400 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=9.504e+07
2023-07-07 08:33:56,122 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=9.668e+07
2023-07-07 08:34:06,828 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=9.832e+07
2023-07-07 08:34:17,484 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=9.996e+07
2023-07-07 08:34:28,312 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 08:34:39,039 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 08:34:49,747 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 08:35:00,499 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 08:35:11,249 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 08:35:21,989 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.098e+08
2023-07-07 08:35:32,671 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 08:35:43,416 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.131e+08
2023-07-07 08:35:54,247 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 08:36:05,046 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.163e+08
2023-07-07 08:36:15,834 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 08:36:26,567 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.196e+08
2023-07-07 08:36:37,258 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.213e+08
2023-07-07 08:36:47,919 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 08:36:58,627 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.245e+08
2023-07-07 08:37:09,414 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.262e+08
2023-07-07 08:37:20,118 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 08:37:30,805 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.294e+08
2023-07-07 08:37:41,529 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 08:37:52,226 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 08:38:02,971 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.344e+08
2023-07-07 08:38:13,815 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.360e+08
2023-07-07 08:38:24,572 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.376e+08
2023-07-07 08:38:35,278 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8500, best=0.58, avg=0.57, std=0.00, steps=1.393e+08
2023-07-07 08:38:46,037 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8600, best=0.61, avg=0.60, std=0.00, steps=1.409e+08
2023-07-07 08:38:56,776 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8700, best=0.63, avg=0.62, std=0.00, steps=1.426e+08
2023-07-07 08:39:07,525 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8800, best=0.65, avg=0.64, std=0.00, steps=1.442e+08
2023-07-07 08:39:18,211 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 8900, best=0.66, avg=0.65, std=0.00, steps=1.458e+08
2023-07-07 08:39:28,944 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9000, best=0.67, avg=0.66, std=0.00, steps=1.475e+08
2023-07-07 08:39:39,639 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9100, best=0.67, avg=0.67, std=0.00, steps=1.491e+08
2023-07-07 08:39:50,372 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9200, best=0.68, avg=0.67, std=0.00, steps=1.507e+08
2023-07-07 08:40:01,135 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9300, best=0.69, avg=0.68, std=0.00, steps=1.524e+08
2023-07-07 08:40:11,866 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9400, best=0.69, avg=0.68, std=0.00, steps=1.540e+08
2023-07-07 08:40:22,622 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9500, best=0.69, avg=0.68, std=0.00, steps=1.557e+08
2023-07-07 08:40:33,350 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9600, best=0.69, avg=0.69, std=0.00, steps=1.573e+08
2023-07-07 08:40:44,049 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9700, best=0.70, avg=0.69, std=0.00, steps=1.589e+08
2023-07-07 08:40:54,800 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9800, best=0.70, avg=0.69, std=0.00, steps=1.606e+08
2023-07-07 08:41:05,507 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 9900, best=0.70, avg=0.70, std=0.00, steps=1.622e+08
2023-07-07 08:41:16,276 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10000, best=0.71, avg=0.70, std=0.00, steps=1.639e+08
2023-07-07 08:41:27,007 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10100, best=0.71, avg=0.70, std=0.00, steps=1.655e+08
2023-07-07 08:41:37,768 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10200, best=0.71, avg=0.70, std=0.00, steps=1.671e+08
2023-07-07 08:41:48,559 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10300, best=0.72, avg=0.71, std=0.00, steps=1.688e+08
2023-07-07 08:41:59,348 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10400, best=0.72, avg=0.71, std=0.00, steps=1.704e+08
2023-07-07 08:42:10,132 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10500, best=0.71, avg=0.71, std=0.00, steps=1.720e+08
2023-07-07 08:42:20,852 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10600, best=0.72, avg=0.71, std=0.00, steps=1.737e+08
2023-07-07 08:42:31,583 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10700, best=0.72, avg=0.71, std=0.00, steps=1.753e+08
2023-07-07 08:42:42,302 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10800, best=0.72, avg=0.71, std=0.00, steps=1.770e+08
2023-07-07 08:42:53,062 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 10900, best=0.72, avg=0.72, std=0.00, steps=1.786e+08
2023-07-07 08:43:03,843 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11000, best=0.73, avg=0.72, std=0.00, steps=1.802e+08
2023-07-07 08:43:14,643 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11100, best=0.73, avg=0.72, std=0.00, steps=1.819e+08
2023-07-07 08:43:25,434 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11200, best=0.73, avg=0.72, std=0.00, steps=1.835e+08
2023-07-07 08:43:36,157 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11300, best=0.73, avg=0.72, std=0.00, steps=1.852e+08
2023-07-07 08:43:46,889 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11400, best=0.73, avg=0.72, std=0.00, steps=1.868e+08
2023-07-07 08:43:57,617 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11500, best=0.73, avg=0.73, std=0.00, steps=1.884e+08
2023-07-07 08:44:08,366 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11600, best=0.74, avg=0.73, std=0.00, steps=1.901e+08
2023-07-07 08:44:19,118 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11700, best=0.74, avg=0.73, std=0.00, steps=1.917e+08
2023-07-07 08:44:29,870 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11800, best=0.74, avg=0.73, std=0.00, steps=1.933e+08
2023-07-07 08:44:40,634 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11900, best=0.74, avg=0.73, std=0.00, steps=1.950e+08
2023-07-07 08:44:51,282 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 1, [Train]: 11999, best=0.74, avg=0.73, std=0.00, steps=1.966e+08
2023-07-07 08:44:51,283 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 08:44:51,309 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 08:44:51,309 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 08:44:51,341 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 08:45:04,777 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=1.862e+06
2023-07-07 08:45:16,880 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=3.705e+06
2023-07-07 08:45:28,962 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=5.548e+06
2023-07-07 08:45:41,033 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=7.391e+06
2023-07-07 08:45:53,147 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=9.234e+06
2023-07-07 08:46:05,253 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.108e+07
2023-07-07 08:46:17,280 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.292e+07
2023-07-07 08:46:29,319 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.476e+07
2023-07-07 08:46:41,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.661e+07
2023-07-07 08:46:53,437 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=1.845e+07
2023-07-07 08:47:05,507 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.029e+07
2023-07-07 08:47:17,566 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.214e+07
2023-07-07 08:47:29,644 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.398e+07
2023-07-07 08:47:41,726 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.582e+07
2023-07-07 08:47:53,808 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=2.767e+07
2023-07-07 08:48:05,901 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.951e+07
2023-07-07 08:48:17,955 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=3.135e+07
2023-07-07 08:48:30,010 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=3.320e+07
2023-07-07 08:48:42,041 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.504e+07
2023-07-07 08:48:54,194 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=3.688e+07
2023-07-07 08:49:06,367 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=3.873e+07
2023-07-07 08:49:18,437 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=4.057e+07
2023-07-07 08:49:30,525 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=4.241e+07
2023-07-07 08:49:42,582 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=4.426e+07
2023-07-07 08:49:54,611 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=4.610e+07
2023-07-07 08:50:06,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=4.794e+07
2023-07-07 08:50:18,763 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=4.978e+07
2023-07-07 08:50:30,803 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=5.163e+07
2023-07-07 08:50:42,898 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=5.347e+07
2023-07-07 08:50:55,001 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=5.531e+07
2023-07-07 08:51:07,131 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=5.716e+07
2023-07-07 08:51:19,164 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=5.900e+07
2023-07-07 08:51:31,211 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=6.084e+07
2023-07-07 08:51:43,277 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=6.269e+07
2023-07-07 08:51:55,398 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=6.453e+07
2023-07-07 08:52:07,498 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=6.637e+07
2023-07-07 08:52:19,602 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=6.822e+07
2023-07-07 08:52:31,694 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=7.006e+07
2023-07-07 08:52:43,804 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=7.190e+07
2023-07-07 08:52:55,937 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 08:53:07,990 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=7.559e+07
2023-07-07 08:53:20,041 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=7.743e+07
2023-07-07 08:53:32,095 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=7.928e+07
2023-07-07 08:53:44,198 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=8.112e+07
2023-07-07 08:53:56,292 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=8.296e+07
2023-07-07 08:54:08,381 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=8.481e+07
2023-07-07 08:54:20,459 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=8.665e+07
2023-07-07 08:54:32,558 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 08:54:44,601 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=9.034e+07
2023-07-07 08:54:56,630 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=9.218e+07
2023-07-07 08:55:08,772 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=9.402e+07
2023-07-07 08:55:20,866 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=9.586e+07
2023-07-07 08:55:32,924 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=9.771e+07
2023-07-07 08:55:45,026 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=9.955e+07
2023-07-07 08:55:57,106 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.014e+08
2023-07-07 08:56:09,135 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 08:56:21,197 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.051e+08
2023-07-07 08:56:33,230 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.069e+08
2023-07-07 08:56:45,338 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.088e+08
2023-07-07 08:56:57,425 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 08:57:09,696 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.125e+08
2023-07-07 08:57:21,772 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.143e+08
2023-07-07 08:57:33,820 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.161e+08
2023-07-07 08:57:45,931 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 08:57:58,112 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.198e+08
2023-07-07 08:58:10,209 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 08:58:22,311 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.235e+08
2023-07-07 08:58:34,362 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 08:58:46,416 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.272e+08
2023-07-07 08:58:58,456 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 08:59:10,549 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.309e+08
2023-07-07 08:59:22,620 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 08:59:34,683 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.346e+08
2023-07-07 08:59:46,738 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.364e+08
2023-07-07 08:59:58,813 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.383e+08
2023-07-07 09:00:10,901 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 09:00:23,057 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.419e+08
2023-07-07 09:00:35,107 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.438e+08
2023-07-07 09:00:47,144 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.456e+08
2023-07-07 09:00:59,206 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 09:01:11,291 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.493e+08
2023-07-07 09:01:23,397 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.512e+08
2023-07-07 09:01:35,588 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.530e+08
2023-07-07 09:01:47,639 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.548e+08
2023-07-07 09:01:59,698 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.567e+08
2023-07-07 09:02:11,773 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.585e+08
2023-07-07 09:02:23,839 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.604e+08
2023-07-07 09:02:35,995 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 09:02:48,012 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.641e+08
2023-07-07 09:03:00,086 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 09:03:12,223 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.677e+08
2023-07-07 09:03:24,323 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 09:03:36,460 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.714e+08
2023-07-07 09:03:48,681 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.733e+08
2023-07-07 09:04:00,876 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=1.751e+08
2023-07-07 09:04:13,039 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 09:04:25,077 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=1.788e+08
2023-07-07 09:04:37,054 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=1.807e+08
2023-07-07 09:04:49,155 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=1.825e+08
2023-07-07 09:05:01,278 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 09:05:13,297 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=1.862e+08
2023-07-07 09:05:25,366 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 09:05:37,454 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=1.899e+08
2023-07-07 09:05:49,698 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 09:06:01,731 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=1.936e+08
2023-07-07 09:06:13,749 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=1.954e+08
2023-07-07 09:06:25,779 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=1.972e+08
2023-07-07 09:06:37,823 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 09:06:49,862 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.009e+08
2023-07-07 09:07:01,867 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 09:07:13,953 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.046e+08
2023-07-07 09:07:26,058 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 09:07:38,085 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.083e+08
2023-07-07 09:07:50,139 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11400, best=0.59, avg=0.58, std=0.00, steps=2.101e+08
2023-07-07 09:08:02,250 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11500, best=0.59, avg=0.58, std=0.00, steps=2.120e+08
2023-07-07 09:08:14,344 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11600, best=0.60, avg=0.59, std=0.00, steps=2.138e+08
2023-07-07 09:08:26,421 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11700, best=0.61, avg=0.60, std=0.00, steps=2.157e+08
2023-07-07 09:08:38,435 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11800, best=0.62, avg=0.61, std=0.00, steps=2.175e+08
2023-07-07 09:08:50,511 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11900, best=0.63, avg=0.62, std=0.00, steps=2.194e+08
2023-07-07 09:09:02,504 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 1, [Train]: 11999, best=0.64, avg=0.63, std=0.00, steps=2.212e+08
2023-07-07 09:09:02,504 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 09:09:02,531 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 09:09:02,531 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 09:09:02,564 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 09:09:17,233 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=2.068e+06
2023-07-07 09:09:30,600 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=4.116e+06
2023-07-07 09:09:44,018 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=6.164e+06
2023-07-07 09:09:57,449 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=8.212e+06
2023-07-07 09:10:10,880 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.026e+07
2023-07-07 09:10:24,297 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.231e+07
2023-07-07 09:10:37,692 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.436e+07
2023-07-07 09:10:51,022 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.640e+07
2023-07-07 09:11:04,380 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.845e+07
2023-07-07 09:11:17,819 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=2.050e+07
2023-07-07 09:11:31,188 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.255e+07
2023-07-07 09:11:44,622 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.460e+07
2023-07-07 09:11:58,059 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=2.664e+07
2023-07-07 09:12:11,436 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.869e+07
2023-07-07 09:12:24,821 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=3.074e+07
2023-07-07 09:12:38,415 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=3.279e+07
2023-07-07 09:12:51,852 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=3.484e+07
2023-07-07 09:13:05,222 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=3.688e+07
2023-07-07 09:13:18,548 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=3.893e+07
2023-07-07 09:13:31,979 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=4.098e+07
2023-07-07 09:13:45,398 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=4.303e+07
2023-07-07 09:13:58,775 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=4.508e+07
2023-07-07 09:14:12,146 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=4.712e+07
2023-07-07 09:14:25,594 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=4.917e+07
2023-07-07 09:14:39,011 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=5.122e+07
2023-07-07 09:14:52,473 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=5.327e+07
2023-07-07 09:15:05,886 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=5.532e+07
2023-07-07 09:15:19,282 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=5.736e+07
2023-07-07 09:15:32,656 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=5.941e+07
2023-07-07 09:15:46,078 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=6.146e+07
2023-07-07 09:15:59,505 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=6.351e+07
2023-07-07 09:16:12,925 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=6.556e+07
2023-07-07 09:16:26,312 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=6.760e+07
2023-07-07 09:16:39,630 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=6.965e+07
2023-07-07 09:16:53,000 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=7.170e+07
2023-07-07 09:17:06,368 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 09:17:19,741 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=7.580e+07
2023-07-07 09:17:33,156 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=7.784e+07
2023-07-07 09:17:46,535 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=7.989e+07
2023-07-07 09:17:59,939 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=8.194e+07
2023-07-07 09:18:13,359 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=8.399e+07
2023-07-07 09:18:26,747 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=8.604e+07
2023-07-07 09:18:40,109 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=8.808e+07
2023-07-07 09:18:53,504 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 09:19:06,892 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=9.218e+07
2023-07-07 09:19:20,232 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=9.423e+07
2023-07-07 09:19:33,599 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=9.628e+07
2023-07-07 09:19:47,013 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=9.832e+07
2023-07-07 09:20:00,413 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.004e+08
2023-07-07 09:20:13,778 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.024e+08
2023-07-07 09:20:27,196 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 09:20:40,608 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 09:20:53,957 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.086e+08
2023-07-07 09:21:07,371 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 09:21:20,731 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.127e+08
2023-07-07 09:21:34,096 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 09:21:47,474 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.168e+08
2023-07-07 09:22:00,862 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.188e+08
2023-07-07 09:22:14,296 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.209e+08
2023-07-07 09:22:27,710 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 09:22:41,127 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.249e+08
2023-07-07 09:22:54,533 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.270e+08
2023-07-07 09:23:07,958 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 09:23:21,388 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 09:23:34,722 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.331e+08
2023-07-07 09:23:48,163 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 09:24:01,588 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.372e+08
2023-07-07 09:24:14,991 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 09:24:28,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.413e+08
2023-07-07 09:24:41,791 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.434e+08
2023-07-07 09:24:55,261 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.454e+08
2023-07-07 09:25:08,684 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 09:25:22,083 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.495e+08
2023-07-07 09:25:35,486 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.516e+08
2023-07-07 09:25:48,904 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.536e+08
2023-07-07 09:26:02,273 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.557e+08
2023-07-07 09:26:15,620 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.577e+08
2023-07-07 09:26:28,980 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 09:26:42,385 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.618e+08
2023-07-07 09:26:55,799 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 09:27:09,191 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 09:27:22,536 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.680e+08
2023-07-07 09:27:35,890 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.700e+08
2023-07-07 09:27:49,345 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 09:28:02,819 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.741e+08
2023-07-07 09:28:16,215 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.761e+08
2023-07-07 09:28:29,652 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.782e+08
2023-07-07 09:28:43,065 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.802e+08
2023-07-07 09:28:56,490 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.823e+08
2023-07-07 09:29:09,902 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 09:29:23,327 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.864e+08
2023-07-07 09:29:36,708 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.884e+08
2023-07-07 09:29:50,103 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.905e+08
2023-07-07 09:30:03,442 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.925e+08
2023-07-07 09:30:16,796 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=1.946e+08
2023-07-07 09:30:30,175 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 09:30:43,534 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=1.987e+08
2023-07-07 09:30:56,876 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=2.007e+08
2023-07-07 09:31:10,264 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 09:31:23,659 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=2.048e+08
2023-07-07 09:31:37,068 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=2.069e+08
2023-07-07 09:31:50,470 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 09:32:03,892 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.110e+08
2023-07-07 09:32:17,251 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 09:32:30,589 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.151e+08
2023-07-07 09:32:43,961 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10600, best=0.59, avg=0.58, std=0.00, steps=2.171e+08
2023-07-07 09:32:57,348 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10700, best=0.62, avg=0.61, std=0.00, steps=2.192e+08
2023-07-07 09:33:10,703 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10800, best=0.63, avg=0.62, std=0.00, steps=2.212e+08
2023-07-07 09:33:24,110 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 10900, best=0.63, avg=0.63, std=0.00, steps=2.233e+08
2023-07-07 09:33:37,547 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11000, best=0.64, avg=0.64, std=0.00, steps=2.253e+08
2023-07-07 09:33:50,928 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11100, best=0.65, avg=0.64, std=0.00, steps=2.273e+08
2023-07-07 09:34:04,318 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11200, best=0.65, avg=0.64, std=0.00, steps=2.294e+08
2023-07-07 09:34:17,708 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11300, best=0.65, avg=0.65, std=0.00, steps=2.314e+08
2023-07-07 09:34:31,109 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11400, best=0.65, avg=0.65, std=0.00, steps=2.335e+08
2023-07-07 09:34:44,502 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11500, best=0.66, avg=0.65, std=0.00, steps=2.355e+08
2023-07-07 09:34:57,924 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11600, best=0.66, avg=0.65, std=0.00, steps=2.376e+08
2023-07-07 09:35:11,258 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11700, best=0.66, avg=0.65, std=0.00, steps=2.396e+08
2023-07-07 09:35:24,703 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11800, best=0.67, avg=0.66, std=0.00, steps=2.417e+08
2023-07-07 09:35:38,139 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11900, best=0.67, avg=0.66, std=0.00, steps=2.437e+08
2023-07-07 09:35:51,422 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 1, [Train]: 11999, best=0.67, avg=0.66, std=0.00, steps=2.458e+08
2023-07-07 09:35:51,423 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 09:35:51,453 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 09:35:51,453 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 09:35:51,484 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 09:36:08,858 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=2.482e+06
2023-07-07 09:36:24,854 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=4.940e+06
2023-07-07 09:36:40,858 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=7.397e+06
2023-07-07 09:36:56,790 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=9.855e+06
2023-07-07 09:37:12,739 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.231e+07
2023-07-07 09:37:28,718 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.477e+07
2023-07-07 09:37:44,692 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=1.723e+07
2023-07-07 09:38:00,710 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=1.969e+07
2023-07-07 09:38:16,728 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=2.214e+07
2023-07-07 09:38:32,730 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=2.460e+07
2023-07-07 09:38:48,741 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=2.706e+07
2023-07-07 09:39:04,729 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=2.952e+07
2023-07-07 09:39:20,749 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=3.197e+07
2023-07-07 09:39:36,755 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=3.443e+07
2023-07-07 09:39:52,777 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=3.689e+07
2023-07-07 09:40:08,800 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=3.935e+07
2023-07-07 09:40:24,809 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=4.180e+07
2023-07-07 09:40:40,856 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=4.426e+07
2023-07-07 09:40:56,831 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=4.672e+07
2023-07-07 09:41:12,845 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=4.918e+07
2023-07-07 09:41:28,879 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=5.163e+07
2023-07-07 09:41:44,870 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=5.409e+07
2023-07-07 09:42:00,888 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=5.655e+07
2023-07-07 09:42:16,903 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=5.901e+07
2023-07-07 09:42:32,830 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=6.146e+07
2023-07-07 09:42:48,823 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=6.392e+07
2023-07-07 09:43:04,830 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=6.638e+07
2023-07-07 09:43:20,764 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=6.884e+07
2023-07-07 09:43:36,772 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=7.129e+07
2023-07-07 09:43:52,788 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=7.375e+07
2023-07-07 09:44:08,804 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=7.621e+07
2023-07-07 09:44:24,713 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=7.867e+07
2023-07-07 09:44:40,616 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=8.113e+07
2023-07-07 09:44:56,527 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=8.358e+07
2023-07-07 09:45:12,554 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=8.604e+07
2023-07-07 09:45:28,593 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=8.850e+07
2023-07-07 09:45:44,594 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=9.096e+07
2023-07-07 09:46:00,648 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=9.341e+07
2023-07-07 09:46:16,682 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=9.587e+07
2023-07-07 09:46:32,663 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=9.833e+07
2023-07-07 09:46:48,664 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.008e+08
2023-07-07 09:47:04,607 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 09:47:20,585 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.057e+08
2023-07-07 09:47:36,593 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 09:47:52,599 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 09:48:08,599 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.131e+08
2023-07-07 09:48:24,603 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.155e+08
2023-07-07 09:48:40,606 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 09:48:56,517 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.204e+08
2023-07-07 09:49:12,506 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 09:49:28,528 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 09:49:44,523 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 09:50:00,548 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.303e+08
2023-07-07 09:50:16,527 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 09:50:32,513 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 09:50:48,493 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.377e+08
2023-07-07 09:51:04,432 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 09:51:20,391 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.426e+08
2023-07-07 09:51:36,425 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.450e+08
2023-07-07 09:51:52,448 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 09:52:08,404 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.499e+08
2023-07-07 09:52:24,361 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6200, best=0.52, avg=0.50, std=0.00, steps=1.524e+08
2023-07-07 09:52:40,328 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.549e+08
2023-07-07 09:52:56,254 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.573e+08
2023-07-07 09:53:12,215 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 09:53:28,224 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 09:53:44,219 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.647e+08
2023-07-07 09:54:00,189 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.671e+08
2023-07-07 09:54:16,224 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 09:54:32,189 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 09:54:48,236 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.745e+08
2023-07-07 09:55:04,264 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 09:55:20,215 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.794e+08
2023-07-07 09:55:36,172 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.819e+08
2023-07-07 09:55:52,158 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 09:56:08,205 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.868e+08
2023-07-07 09:56:24,274 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.893e+08
2023-07-07 09:56:40,247 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 09:56:56,180 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.942e+08
2023-07-07 09:57:12,262 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 09:57:28,349 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 09:57:44,336 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.015e+08
2023-07-07 09:58:00,257 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.040e+08
2023-07-07 09:58:16,290 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 09:58:32,352 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 09:58:48,438 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.114e+08
2023-07-07 09:59:04,453 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=2.138e+08
2023-07-07 09:59:20,422 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=2.163e+08
2023-07-07 09:59:36,401 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.188e+08
2023-07-07 09:59:52,408 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 10:00:08,499 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=2.237e+08
2023-07-07 10:00:24,505 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=2.261e+08
2023-07-07 10:00:40,519 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=2.286e+08
2023-07-07 10:00:56,544 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=2.310e+08
2023-07-07 10:01:12,596 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=2.335e+08
2023-07-07 10:01:28,548 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 10:01:44,448 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=2.384e+08
2023-07-07 10:02:00,478 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=2.409e+08
2023-07-07 10:02:16,435 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=2.433e+08
2023-07-07 10:02:32,373 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 10:02:48,370 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=2.482e+08
2023-07-07 10:03:04,388 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 10:03:20,485 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.532e+08
2023-07-07 10:03:36,465 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 10:03:52,414 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 10:04:08,365 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=2.605e+08
2023-07-07 10:04:24,375 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=2.630e+08
2023-07-07 10:04:40,401 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=2.654e+08
2023-07-07 10:04:56,357 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.679e+08
2023-07-07 10:05:12,323 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.704e+08
2023-07-07 10:05:28,294 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.728e+08
2023-07-07 10:05:44,294 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 10:06:00,306 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.777e+08
2023-07-07 10:06:16,335 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=2.802e+08
2023-07-07 10:06:32,307 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=2.826e+08
2023-07-07 10:06:48,350 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 10:07:04,397 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=2.876e+08
2023-07-07 10:07:20,461 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=2.900e+08
2023-07-07 10:07:36,505 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=2.925e+08
2023-07-07 10:07:52,325 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 1, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 10:07:52,326 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 10:07:52,352 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 10:07:52,352 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 10:07:52,384 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 10:08:15,356 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.310e+06
2023-07-07 10:08:36,465 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=6.586e+06
2023-07-07 10:08:57,585 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=9.863e+06
2023-07-07 10:09:18,723 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.314e+07
2023-07-07 10:09:39,908 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.642e+07
2023-07-07 10:10:01,177 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=1.969e+07
2023-07-07 10:10:22,428 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.297e+07
2023-07-07 10:10:43,590 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.625e+07
2023-07-07 10:11:04,771 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=2.952e+07
2023-07-07 10:11:25,894 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.280e+07
2023-07-07 10:11:46,992 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=3.608e+07
2023-07-07 10:12:08,155 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=3.935e+07
2023-07-07 10:12:29,403 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.263e+07
2023-07-07 10:12:50,580 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=4.591e+07
2023-07-07 10:13:11,703 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=4.918e+07
2023-07-07 10:13:32,889 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.246e+07
2023-07-07 10:13:54,046 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=5.574e+07
2023-07-07 10:14:15,198 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=5.902e+07
2023-07-07 10:14:36,319 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=6.229e+07
2023-07-07 10:14:57,563 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=6.557e+07
2023-07-07 10:15:18,723 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=6.885e+07
2023-07-07 10:15:39,912 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=7.212e+07
2023-07-07 10:16:01,085 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=7.540e+07
2023-07-07 10:16:22,194 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=7.868e+07
2023-07-07 10:16:43,350 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=8.195e+07
2023-07-07 10:17:04,502 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=8.523e+07
2023-07-07 10:17:25,626 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=8.851e+07
2023-07-07 10:17:46,849 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=9.178e+07
2023-07-07 10:18:08,096 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=9.506e+07
2023-07-07 10:18:29,256 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=9.834e+07
2023-07-07 10:18:50,361 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 10:19:11,527 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 10:19:32,725 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 10:19:53,857 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 10:20:15,150 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 10:20:36,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 10:20:57,432 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.213e+08
2023-07-07 10:21:18,586 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.246e+08
2023-07-07 10:21:39,778 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 10:22:00,974 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 10:22:22,306 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.344e+08
2023-07-07 10:22:43,460 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.377e+08
2023-07-07 10:23:04,565 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.409e+08
2023-07-07 10:23:25,753 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.442e+08
2023-07-07 10:23:46,889 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 10:24:08,056 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.508e+08
2023-07-07 10:24:29,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.540e+08
2023-07-07 10:24:50,544 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.573e+08
2023-07-07 10:25:11,754 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.606e+08
2023-07-07 10:25:33,016 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 10:25:54,203 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.671e+08
2023-07-07 10:26:15,452 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.704e+08
2023-07-07 10:26:36,562 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.737e+08
2023-07-07 10:26:57,791 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 10:27:18,965 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.803e+08
2023-07-07 10:27:40,166 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.835e+08
2023-07-07 10:28:01,337 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.868e+08
2023-07-07 10:28:22,552 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.901e+08
2023-07-07 10:28:43,679 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.934e+08
2023-07-07 10:29:04,832 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 10:29:26,058 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.999e+08
2023-07-07 10:29:47,230 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.032e+08
2023-07-07 10:30:08,396 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 10:30:29,526 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.097e+08
2023-07-07 10:30:50,849 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 10:31:12,108 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.163e+08
2023-07-07 10:31:33,231 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.196e+08
2023-07-07 10:31:54,442 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 10:32:15,606 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.261e+08
2023-07-07 10:32:36,665 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.294e+08
2023-07-07 10:32:57,796 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.327e+08
2023-07-07 10:33:19,029 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 10:33:40,147 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.392e+08
2023-07-07 10:34:01,302 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.425e+08
2023-07-07 10:34:22,478 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 10:34:43,631 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.491e+08
2023-07-07 10:35:04,826 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.523e+08
2023-07-07 10:35:26,036 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 10:35:47,201 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.589e+08
2023-07-07 10:36:08,389 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.622e+08
2023-07-07 10:36:29,600 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.655e+08
2023-07-07 10:36:50,761 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.687e+08
2023-07-07 10:37:11,889 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.720e+08
2023-07-07 10:37:33,010 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 10:37:54,158 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 10:38:15,315 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.818e+08
2023-07-07 10:38:36,464 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 10:38:57,574 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=2.884e+08
2023-07-07 10:39:18,669 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.917e+08
2023-07-07 10:39:39,786 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 10:40:00,918 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=2.982e+08
2023-07-07 10:40:22,045 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.015e+08
2023-07-07 10:40:43,164 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.048e+08
2023-07-07 10:41:04,348 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.081e+08
2023-07-07 10:41:25,523 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 10:41:46,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.146e+08
2023-07-07 10:42:07,875 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.179e+08
2023-07-07 10:42:28,987 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.212e+08
2023-07-07 10:42:50,139 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.244e+08
2023-07-07 10:43:11,257 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.277e+08
2023-07-07 10:43:32,438 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.310e+08
2023-07-07 10:43:53,704 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 10:44:14,866 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.375e+08
2023-07-07 10:44:36,140 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.408e+08
2023-07-07 10:44:57,316 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.441e+08
2023-07-07 10:45:18,436 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.474e+08
2023-07-07 10:45:39,641 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.507e+08
2023-07-07 10:46:00,765 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.539e+08
2023-07-07 10:46:21,865 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=3.572e+08
2023-07-07 10:46:42,982 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=3.605e+08
2023-07-07 10:47:04,181 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=3.638e+08
2023-07-07 10:47:25,376 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=3.670e+08
2023-07-07 10:47:46,563 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=3.703e+08
2023-07-07 10:48:07,715 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=3.736e+08
2023-07-07 10:48:28,943 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=3.769e+08
2023-07-07 10:48:50,087 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=3.801e+08
2023-07-07 10:49:11,209 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=3.834e+08
2023-07-07 10:49:32,418 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=3.867e+08
2023-07-07 10:49:53,617 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=3.900e+08
2023-07-07 10:50:14,742 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 1, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=3.932e+08
2023-07-07 10:50:14,743 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 10:50:14,768 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 10:50:14,768 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 10:50:14,805 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 10:50:38,889 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.516e+06
2023-07-07 10:51:01,331 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=6.998e+06
2023-07-07 10:51:23,860 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.048e+07
2023-07-07 10:51:46,371 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.396e+07
2023-07-07 10:52:08,984 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.744e+07
2023-07-07 10:52:31,470 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.092e+07
2023-07-07 10:52:53,994 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.441e+07
2023-07-07 10:53:16,440 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.789e+07
2023-07-07 10:53:38,945 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.137e+07
2023-07-07 10:54:01,447 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.485e+07
2023-07-07 10:54:24,026 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=3.833e+07
2023-07-07 10:54:46,481 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.181e+07
2023-07-07 10:55:08,990 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.530e+07
2023-07-07 10:55:31,415 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=4.878e+07
2023-07-07 10:55:53,940 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=5.226e+07
2023-07-07 10:56:16,648 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.574e+07
2023-07-07 10:56:39,200 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=5.922e+07
2023-07-07 10:57:01,727 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=6.270e+07
2023-07-07 10:57:24,189 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=6.619e+07
2023-07-07 10:57:46,698 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=6.967e+07
2023-07-07 10:58:09,211 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=7.315e+07
2023-07-07 10:58:31,807 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=7.663e+07
2023-07-07 10:58:54,297 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=8.011e+07
2023-07-07 10:59:16,791 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=8.359e+07
2023-07-07 10:59:39,310 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=8.707e+07
2023-07-07 11:00:01,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=9.056e+07
2023-07-07 11:00:24,201 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=9.404e+07
2023-07-07 11:00:46,659 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=9.752e+07
2023-07-07 11:01:09,160 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.010e+08
2023-07-07 11:01:31,651 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 11:01:54,215 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.080e+08
2023-07-07 11:02:16,712 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 11:02:39,410 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.149e+08
2023-07-07 11:03:01,969 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.184e+08
2023-07-07 11:03:24,479 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.219e+08
2023-07-07 11:03:46,948 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 11:04:09,432 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.289e+08
2023-07-07 11:04:31,916 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.323e+08
2023-07-07 11:04:54,366 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.358e+08
2023-07-07 11:05:16,787 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 11:05:39,304 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.428e+08
2023-07-07 11:06:01,731 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.463e+08
2023-07-07 11:06:24,173 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.497e+08
2023-07-07 11:06:46,676 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.532e+08
2023-07-07 11:07:09,141 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.567e+08
2023-07-07 11:07:31,698 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.602e+08
2023-07-07 11:07:54,264 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.637e+08
2023-07-07 11:08:16,730 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.672e+08
2023-07-07 11:08:39,279 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.706e+08
2023-07-07 11:09:01,784 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.741e+08
2023-07-07 11:09:24,191 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.776e+08
2023-07-07 11:09:46,707 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.811e+08
2023-07-07 11:10:09,043 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.846e+08
2023-07-07 11:10:31,515 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 11:10:53,946 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.915e+08
2023-07-07 11:11:16,440 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.950e+08
2023-07-07 11:11:39,010 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.985e+08
2023-07-07 11:12:01,544 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.020e+08
2023-07-07 11:12:23,952 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.054e+08
2023-07-07 11:12:46,448 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 11:13:08,926 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.124e+08
2023-07-07 11:13:31,491 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.159e+08
2023-07-07 11:13:54,033 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.194e+08
2023-07-07 11:14:16,493 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 11:14:39,054 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.263e+08
2023-07-07 11:15:01,546 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.298e+08
2023-07-07 11:15:24,057 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.333e+08
2023-07-07 11:15:46,695 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.368e+08
2023-07-07 11:16:09,115 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.403e+08
2023-07-07 11:16:31,499 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.437e+08
2023-07-07 11:16:53,984 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.472e+08
2023-07-07 11:17:16,469 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 11:17:39,011 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.542e+08
2023-07-07 11:18:01,489 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.577e+08
2023-07-07 11:18:23,939 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.612e+08
2023-07-07 11:18:46,302 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.646e+08
2023-07-07 11:19:08,744 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.681e+08
2023-07-07 11:19:31,151 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.716e+08
2023-07-07 11:19:53,689 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.751e+08
2023-07-07 11:20:16,101 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 11:20:38,488 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.820e+08
2023-07-07 11:21:00,861 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.855e+08
2023-07-07 11:21:23,293 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.890e+08
2023-07-07 11:21:45,702 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.925e+08
2023-07-07 11:22:08,100 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.960e+08
2023-07-07 11:22:30,536 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.995e+08
2023-07-07 11:22:52,974 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.029e+08
2023-07-07 11:23:15,340 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.064e+08
2023-07-07 11:23:37,800 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.099e+08
2023-07-07 11:24:00,290 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.134e+08
2023-07-07 11:24:22,713 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.169e+08
2023-07-07 11:24:45,146 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.203e+08
2023-07-07 11:25:07,594 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.238e+08
2023-07-07 11:25:30,126 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.273e+08
2023-07-07 11:25:52,566 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.308e+08
2023-07-07 11:26:15,110 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 11:26:37,680 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.378e+08
2023-07-07 11:27:00,139 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.412e+08
2023-07-07 11:27:22,632 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.447e+08
2023-07-07 11:27:45,029 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.482e+08
2023-07-07 11:28:07,513 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.517e+08
2023-07-07 11:28:30,030 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.552e+08
2023-07-07 11:28:52,482 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.586e+08
2023-07-07 11:29:14,853 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.621e+08
2023-07-07 11:29:37,250 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.656e+08
2023-07-07 11:29:59,643 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.691e+08
2023-07-07 11:30:22,133 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.726e+08
2023-07-07 11:30:44,510 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 11:31:06,987 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=3.795e+08
2023-07-07 11:31:29,410 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=3.830e+08
2023-07-07 11:31:51,816 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=3.865e+08
2023-07-07 11:32:14,247 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=3.900e+08
2023-07-07 11:32:36,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=3.935e+08
2023-07-07 11:32:59,221 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=3.969e+08
2023-07-07 11:33:21,634 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.004e+08
2023-07-07 11:33:44,125 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.039e+08
2023-07-07 11:34:06,614 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.074e+08
2023-07-07 11:34:29,085 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.109e+08
2023-07-07 11:34:51,554 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.143e+08
2023-07-07 11:35:13,689 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 1, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.178e+08
2023-07-07 11:35:13,690 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 11:35:13,715 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 11:35:13,715 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 11:35:13,749 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 11:35:38,897 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=3.723e+06
2023-07-07 11:36:02,547 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=7.410e+06
2023-07-07 11:36:26,351 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.110e+07
2023-07-07 11:36:50,105 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.478e+07
2023-07-07 11:37:13,791 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.847e+07
2023-07-07 11:37:37,586 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.216e+07
2023-07-07 11:38:01,319 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.584e+07
2023-07-07 11:38:25,077 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.953e+07
2023-07-07 11:38:48,895 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.321e+07
2023-07-07 11:39:12,633 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=3.690e+07
2023-07-07 11:39:36,377 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=4.059e+07
2023-07-07 11:40:00,244 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.427e+07
2023-07-07 11:40:24,035 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=4.796e+07
2023-07-07 11:40:47,765 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=5.165e+07
2023-07-07 11:41:11,665 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=5.533e+07
2023-07-07 11:41:35,518 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=5.902e+07
2023-07-07 11:41:59,328 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=6.271e+07
2023-07-07 11:42:23,020 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=6.639e+07
2023-07-07 11:42:46,693 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=7.008e+07
2023-07-07 11:43:10,410 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=7.376e+07
2023-07-07 11:43:34,227 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=7.745e+07
2023-07-07 11:43:57,969 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=8.114e+07
2023-07-07 11:44:21,680 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=8.482e+07
2023-07-07 11:44:45,352 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=8.851e+07
2023-07-07 11:45:09,101 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=9.220e+07
2023-07-07 11:45:32,800 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=9.588e+07
2023-07-07 11:45:56,534 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=9.957e+07
2023-07-07 11:46:20,236 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=1.033e+08
2023-07-07 11:46:43,974 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.069e+08
2023-07-07 11:47:07,745 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 11:47:31,540 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.143e+08
2023-07-07 11:47:55,197 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 11:48:18,966 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 11:48:42,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 11:49:06,642 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.291e+08
2023-07-07 11:49:30,365 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 11:49:54,175 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.364e+08
2023-07-07 11:50:17,977 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 11:50:41,717 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.438e+08
2023-07-07 11:51:05,426 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 11:51:29,142 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.512e+08
2023-07-07 11:51:53,011 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.549e+08
2023-07-07 11:52:16,872 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.586e+08
2023-07-07 11:52:40,592 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 11:53:04,283 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 11:53:28,085 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 11:53:51,804 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.733e+08
2023-07-07 11:54:15,490 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 11:54:39,159 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=1.807e+08
2023-07-07 11:55:02,828 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=1.844e+08
2023-07-07 11:55:26,573 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.880e+08
2023-07-07 11:55:50,278 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=1.917e+08
2023-07-07 11:56:13,997 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.954e+08
2023-07-07 11:56:37,780 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 11:57:01,467 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 11:57:25,190 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=2.065e+08
2023-07-07 11:57:48,959 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=2.102e+08
2023-07-07 11:58:12,717 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.138e+08
2023-07-07 11:58:36,415 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.175e+08
2023-07-07 11:59:00,194 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 11:59:24,065 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.249e+08
2023-07-07 11:59:47,931 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.286e+08
2023-07-07 12:00:11,672 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.323e+08
2023-07-07 12:00:35,438 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 12:00:59,165 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.397e+08
2023-07-07 12:01:22,926 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.433e+08
2023-07-07 12:01:46,680 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.470e+08
2023-07-07 12:02:10,369 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.507e+08
2023-07-07 12:02:34,025 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.544e+08
2023-07-07 12:02:57,757 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 12:03:21,509 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.618e+08
2023-07-07 12:03:45,268 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.655e+08
2023-07-07 12:04:09,093 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.691e+08
2023-07-07 12:04:32,899 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.728e+08
2023-07-07 12:04:56,726 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.765e+08
2023-07-07 12:05:20,527 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.802e+08
2023-07-07 12:05:44,228 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.839e+08
2023-07-07 12:06:08,061 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.876e+08
2023-07-07 12:06:31,756 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.913e+08
2023-07-07 12:06:55,486 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 12:07:19,230 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.986e+08
2023-07-07 12:07:42,937 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=3.023e+08
2023-07-07 12:08:06,632 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=3.060e+08
2023-07-07 12:08:30,345 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=3.097e+08
2023-07-07 12:08:54,090 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=3.134e+08
2023-07-07 12:09:17,894 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=3.171e+08
2023-07-07 12:09:41,672 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.208e+08
2023-07-07 12:10:05,479 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.244e+08
2023-07-07 12:10:29,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.281e+08
2023-07-07 12:10:53,030 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.318e+08
2023-07-07 12:11:16,763 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.355e+08
2023-07-07 12:11:40,468 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.392e+08
2023-07-07 12:12:04,263 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.429e+08
2023-07-07 12:12:28,100 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.466e+08
2023-07-07 12:12:51,899 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.502e+08
2023-07-07 12:13:15,697 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.539e+08
2023-07-07 12:13:39,506 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.576e+08
2023-07-07 12:14:03,221 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.613e+08
2023-07-07 12:14:27,019 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.650e+08
2023-07-07 12:14:50,782 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.687e+08
2023-07-07 12:15:14,615 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.724e+08
2023-07-07 12:15:38,459 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 12:16:02,274 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.797e+08
2023-07-07 12:16:26,128 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.834e+08
2023-07-07 12:16:49,939 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.871e+08
2023-07-07 12:17:13,687 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.908e+08
2023-07-07 12:17:37,492 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.945e+08
2023-07-07 12:18:01,238 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.982e+08
2023-07-07 12:18:25,039 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=4.019e+08
2023-07-07 12:18:48,865 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 12:19:12,563 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=4.092e+08
2023-07-07 12:19:36,283 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=4.129e+08
2023-07-07 12:19:59,982 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=4.166e+08
2023-07-07 12:20:23,657 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=4.203e+08
2023-07-07 12:20:47,296 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.240e+08
2023-07-07 12:21:10,951 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.277e+08
2023-07-07 12:21:34,750 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.313e+08
2023-07-07 12:21:58,471 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.350e+08
2023-07-07 12:22:22,358 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.387e+08
2023-07-07 12:22:45,899 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 1, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.424e+08
2023-07-07 12:22:45,900 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 12:22:45,927 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 12:22:45,927 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 12:22:45,961 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 12:23:13,857 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=4.137e+06
2023-07-07 12:23:40,418 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=8.233e+06
2023-07-07 12:24:07,213 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=1.233e+07
2023-07-07 12:24:33,500 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=1.642e+07
2023-07-07 12:24:59,964 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=2.052e+07
2023-07-07 12:25:26,235 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=2.462e+07
2023-07-07 12:25:52,465 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.871e+07
2023-07-07 12:26:18,855 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=3.281e+07
2023-07-07 12:26:45,235 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.690e+07
2023-07-07 12:27:11,535 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=4.100e+07
2023-07-07 12:27:37,801 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=4.510e+07
2023-07-07 12:28:04,231 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.919e+07
2023-07-07 12:28:30,658 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1300, best=0.51, avg=0.50, std=0.00, steps=5.329e+07
2023-07-07 12:28:57,022 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=5.738e+07
2023-07-07 12:29:23,397 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1500, best=0.51, avg=0.50, std=0.00, steps=6.148e+07
2023-07-07 12:29:49,775 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=6.558e+07
2023-07-07 12:30:16,148 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1700, best=0.51, avg=0.50, std=0.00, steps=6.967e+07
2023-07-07 12:30:42,594 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=7.377e+07
2023-07-07 12:31:09,004 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=7.786e+07
2023-07-07 12:31:35,315 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=8.196e+07
2023-07-07 12:32:01,648 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=8.606e+07
2023-07-07 12:32:28,012 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=9.015e+07
2023-07-07 12:32:54,306 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=9.425e+07
2023-07-07 12:33:20,711 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=9.834e+07
2023-07-07 12:33:47,144 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=1.024e+08
2023-07-07 12:34:13,499 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 12:34:39,803 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 12:35:06,259 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 12:35:32,577 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.188e+08
2023-07-07 12:35:58,881 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 12:36:25,269 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.270e+08
2023-07-07 12:36:51,726 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3200, best=0.50, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 12:37:18,193 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 12:37:44,485 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 12:38:10,818 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.434e+08
2023-07-07 12:38:37,293 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3600, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 12:39:03,647 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3700, best=0.51, avg=0.50, std=0.00, steps=1.516e+08
2023-07-07 12:39:29,975 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.557e+08
2023-07-07 12:39:56,304 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 12:40:22,623 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 12:40:49,039 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4100, best=0.51, avg=0.50, std=0.00, steps=1.680e+08
2023-07-07 12:41:15,419 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 12:41:41,729 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=1.762e+08
2023-07-07 12:42:08,208 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=1.803e+08
2023-07-07 12:42:34,646 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=1.844e+08
2023-07-07 12:43:01,015 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.885e+08
2023-07-07 12:43:27,406 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.926e+08
2023-07-07 12:43:53,830 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 12:44:20,263 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=2.007e+08
2023-07-07 12:44:46,649 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=2.048e+08
2023-07-07 12:45:12,947 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 12:45:39,298 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 12:46:05,586 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=2.171e+08
2023-07-07 12:46:31,911 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 12:46:58,210 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=2.253e+08
2023-07-07 12:47:24,533 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=2.294e+08
2023-07-07 12:47:50,858 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=2.335e+08
2023-07-07 12:48:17,239 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=2.376e+08
2023-07-07 12:48:43,662 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=2.417e+08
2023-07-07 12:49:10,155 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 12:49:36,491 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=2.499e+08
2023-07-07 12:50:02,778 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.540e+08
2023-07-07 12:50:29,291 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 12:50:55,605 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=2.622e+08
2023-07-07 12:51:21,910 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.663e+08
2023-07-07 12:51:48,328 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.704e+08
2023-07-07 12:52:14,789 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=2.745e+08
2023-07-07 12:52:41,028 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 12:53:07,306 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.827e+08
2023-07-07 12:53:33,508 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.868e+08
2023-07-07 12:53:59,750 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.909e+08
2023-07-07 12:54:26,138 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.950e+08
2023-07-07 12:54:52,518 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.990e+08
2023-07-07 12:55:18,761 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=3.031e+08
2023-07-07 12:55:45,083 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=3.072e+08
2023-07-07 12:56:11,444 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 12:56:37,759 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=3.154e+08
2023-07-07 12:57:04,072 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=3.195e+08
2023-07-07 12:57:30,369 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=3.236e+08
2023-07-07 12:57:56,679 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=3.277e+08
2023-07-07 12:58:23,036 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=3.318e+08
2023-07-07 12:58:49,334 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=3.359e+08
2023-07-07 12:59:15,659 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=3.400e+08
2023-07-07 12:59:42,005 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=3.441e+08
2023-07-07 13:00:08,294 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=3.482e+08
2023-07-07 13:00:34,589 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=3.523e+08
2023-07-07 13:01:00,862 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.564e+08
2023-07-07 13:01:27,221 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.605e+08
2023-07-07 13:01:53,624 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.646e+08
2023-07-07 13:02:19,989 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.687e+08
2023-07-07 13:02:46,225 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.728e+08
2023-07-07 13:03:12,515 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.769e+08
2023-07-07 13:03:38,815 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.810e+08
2023-07-07 13:04:05,117 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.851e+08
2023-07-07 13:04:31,310 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.892e+08
2023-07-07 13:04:57,672 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.933e+08
2023-07-07 13:05:24,069 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.974e+08
2023-07-07 13:05:50,328 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=4.014e+08
2023-07-07 13:06:16,556 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 13:06:42,807 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=4.096e+08
2023-07-07 13:07:09,131 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=4.137e+08
2023-07-07 13:07:35,477 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=4.178e+08
2023-07-07 13:08:01,762 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=4.219e+08
2023-07-07 13:08:28,112 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=4.260e+08
2023-07-07 13:08:54,466 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=4.301e+08
2023-07-07 13:09:20,839 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=4.342e+08
2023-07-07 13:09:47,051 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=4.383e+08
2023-07-07 13:10:13,312 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=4.424e+08
2023-07-07 13:10:39,660 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=4.465e+08
2023-07-07 13:11:06,006 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=4.506e+08
2023-07-07 13:11:32,261 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=4.547e+08
2023-07-07 13:11:58,476 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=4.588e+08
2023-07-07 13:12:24,809 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=4.629e+08
2023-07-07 13:12:51,030 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=4.670e+08
2023-07-07 13:13:17,421 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.711e+08
2023-07-07 13:13:43,780 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.752e+08
2023-07-07 13:14:10,009 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.793e+08
2023-07-07 13:14:36,387 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.834e+08
2023-07-07 13:15:02,620 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.875e+08
2023-07-07 13:15:28,743 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 1, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.915e+08
2023-07-07 13:15:28,744 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:15:28,770 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:15:28,770 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:15:28,805 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:15:32,957 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=4.137e+05
2023-07-07 13:15:35,871 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=8.233e+05
2023-07-07 13:15:38,791 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.233e+06
2023-07-07 13:15:41,681 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=1.642e+06
2023-07-07 13:15:44,570 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=2.052e+06
2023-07-07 13:15:47,472 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=2.462e+06
2023-07-07 13:15:50,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=2.871e+06
2023-07-07 13:15:53,264 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=3.281e+06
2023-07-07 13:15:56,156 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=3.690e+06
2023-07-07 13:15:59,060 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=4.100e+06
2023-07-07 13:16:01,961 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=4.510e+06
2023-07-07 13:16:04,854 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=4.919e+06
2023-07-07 13:16:07,759 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=5.329e+06
2023-07-07 13:16:10,671 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=5.738e+06
2023-07-07 13:16:13,584 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=6.148e+06
2023-07-07 13:16:16,486 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=6.558e+06
2023-07-07 13:16:19,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=6.967e+06
2023-07-07 13:16:22,257 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=7.377e+06
2023-07-07 13:16:25,144 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=7.786e+06
2023-07-07 13:16:28,033 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=8.196e+06
2023-07-07 13:16:30,916 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=8.606e+06
2023-07-07 13:16:33,806 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=9.015e+06
2023-07-07 13:16:36,693 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=9.425e+06
2023-07-07 13:16:39,584 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=9.834e+06
2023-07-07 13:16:42,490 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.024e+07
2023-07-07 13:16:45,397 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.065e+07
2023-07-07 13:16:48,289 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.106e+07
2023-07-07 13:16:51,187 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.147e+07
2023-07-07 13:16:54,084 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.188e+07
2023-07-07 13:16:56,971 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 13:16:59,864 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.270e+07
2023-07-07 13:17:02,760 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.311e+07
2023-07-07 13:17:05,654 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 13:17:08,552 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 13:17:11,448 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=1.434e+07
2023-07-07 13:17:14,346 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 13:17:17,237 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=1.516e+07
2023-07-07 13:17:20,120 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 13:17:22,995 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 13:17:25,877 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 13:17:28,767 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=1.680e+07
2023-07-07 13:17:31,657 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 13:17:34,534 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=1.762e+07
2023-07-07 13:17:37,435 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 13:17:40,313 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 13:17:43,193 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 13:17:46,073 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=1.926e+07
2023-07-07 13:17:48,943 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=1.966e+07
2023-07-07 13:17:51,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=2.007e+07
2023-07-07 13:17:54,719 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=2.048e+07
2023-07-07 13:17:57,644 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=2.089e+07
2023-07-07 13:18:00,562 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=2.130e+07
2023-07-07 13:18:03,471 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=2.171e+07
2023-07-07 13:18:06,380 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 13:18:09,282 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=2.253e+07
2023-07-07 13:18:12,182 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=2.294e+07
2023-07-07 13:18:15,088 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 13:18:17,998 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 13:18:20,876 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=2.417e+07
2023-07-07 13:18:23,772 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 13:18:26,692 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=2.499e+07
2023-07-07 13:18:29,628 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 13:18:32,549 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 13:18:35,432 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 13:18:38,326 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 13:18:41,217 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 13:18:44,114 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=2.745e+07
2023-07-07 13:18:47,005 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 13:18:49,947 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 13:18:52,866 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 13:18:55,772 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=2.909e+07
2023-07-07 13:18:58,727 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 13:19:01,640 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=2.990e+07
2023-07-07 13:19:04,560 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=3.031e+07
2023-07-07 13:19:07,473 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=3.072e+07
2023-07-07 13:19:10,373 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=3.113e+07
2023-07-07 13:19:13,282 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=3.154e+07
2023-07-07 13:19:16,204 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 13:19:19,125 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=3.236e+07
2023-07-07 13:19:22,026 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=3.277e+07
2023-07-07 13:19:24,927 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 13:19:27,830 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=3.359e+07
2023-07-07 13:19:30,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=3.400e+07
2023-07-07 13:19:33,666 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 13:19:36,595 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=3.482e+07
2023-07-07 13:19:39,529 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 13:19:42,421 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 13:19:45,312 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8800, best=0.71, avg=0.69, std=0.01, steps=3.605e+07
2023-07-07 13:19:48,199 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 8900, best=0.78, avg=0.76, std=0.01, steps=3.646e+07
2023-07-07 13:19:51,078 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9000, best=0.81, avg=0.80, std=0.01, steps=3.687e+07
2023-07-07 13:19:53,969 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=3.728e+07
2023-07-07 13:19:56,875 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9200, best=0.88, avg=0.86, std=0.01, steps=3.769e+07
2023-07-07 13:19:59,801 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9300, best=0.89, avg=0.87, std=0.01, steps=3.810e+07
2023-07-07 13:20:02,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9400, best=0.90, avg=0.89, std=0.00, steps=3.851e+07
2023-07-07 13:20:05,575 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9500, best=0.90, avg=0.90, std=0.00, steps=3.892e+07
2023-07-07 13:20:08,470 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9600, best=0.92, avg=0.91, std=0.00, steps=3.933e+07
2023-07-07 13:20:11,379 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9700, best=0.93, avg=0.92, std=0.00, steps=3.974e+07
2023-07-07 13:20:14,261 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9800, best=0.94, avg=0.93, std=0.00, steps=4.014e+07
2023-07-07 13:20:17,155 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 9900, best=0.94, avg=0.94, std=0.00, steps=4.055e+07
2023-07-07 13:20:20,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10000, best=0.95, avg=0.94, std=0.00, steps=4.096e+07
2023-07-07 13:20:22,943 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10100, best=0.95, avg=0.94, std=0.00, steps=4.137e+07
2023-07-07 13:20:25,847 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10200, best=0.95, avg=0.94, std=0.00, steps=4.178e+07
2023-07-07 13:20:28,769 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10300, best=0.95, avg=0.94, std=0.00, steps=4.219e+07
2023-07-07 13:20:31,689 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10400, best=0.95, avg=0.94, std=0.00, steps=4.260e+07
2023-07-07 13:20:34,610 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10500, best=0.95, avg=0.94, std=0.00, steps=4.301e+07
2023-07-07 13:20:37,546 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10600, best=0.95, avg=0.95, std=0.00, steps=4.342e+07
2023-07-07 13:20:40,457 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10700, best=0.95, avg=0.95, std=0.00, steps=4.383e+07
2023-07-07 13:20:43,352 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10800, best=0.95, avg=0.95, std=0.00, steps=4.424e+07
2023-07-07 13:20:46,243 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 10900, best=0.97, avg=0.96, std=0.00, steps=4.465e+07
2023-07-07 13:20:49,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11000, best=0.98, avg=0.97, std=0.00, steps=4.506e+07
2023-07-07 13:20:52,035 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11100, best=0.98, avg=0.98, std=0.00, steps=4.547e+07
2023-07-07 13:20:54,952 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11200, best=0.99, avg=0.99, std=0.00, steps=4.588e+07
2023-07-07 13:20:57,871 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11300, best=0.99, avg=0.99, std=0.00, steps=4.629e+07
2023-07-07 13:21:00,785 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11400, best=1.00, avg=1.00, std=0.00, steps=4.670e+07
2023-07-07 13:21:03,703 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11500, best=1.00, avg=1.00, std=0.00, steps=4.711e+07
2023-07-07 13:21:06,612 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11600, best=1.00, avg=1.00, std=0.00, steps=4.752e+07
2023-07-07 13:21:09,508 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11700, best=1.00, avg=1.00, std=0.00, steps=4.793e+07
2023-07-07 13:21:12,428 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11800, best=1.00, avg=1.00, std=0.00, steps=4.834e+07
2023-07-07 13:21:15,329 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11900, best=1.00, avg=1.00, std=0.00, steps=4.875e+07
2023-07-07 13:21:18,203 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 2, [Train]: 11999, best=1.00, avg=1.00, std=0.00, steps=4.915e+07
2023-07-07 13:21:18,203 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:21:18,228 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:21:18,228 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:21:18,260 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:21:23,700 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=6.205e+05
2023-07-07 13:21:27,908 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.235e+06
2023-07-07 13:21:32,145 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.849e+06
2023-07-07 13:21:36,371 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=2.464e+06
2023-07-07 13:21:40,556 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=3.078e+06
2023-07-07 13:21:44,745 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=3.693e+06
2023-07-07 13:21:48,923 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=4.307e+06
2023-07-07 13:21:53,105 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=4.921e+06
2023-07-07 13:21:57,277 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=5.536e+06
2023-07-07 13:22:01,465 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=6.150e+06
2023-07-07 13:22:05,660 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=6.765e+06
2023-07-07 13:22:09,861 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=7.379e+06
2023-07-07 13:22:14,034 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=7.993e+06
2023-07-07 13:22:18,205 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=8.608e+06
2023-07-07 13:22:22,370 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=9.222e+06
2023-07-07 13:22:26,553 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=9.837e+06
2023-07-07 13:22:30,709 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.045e+07
2023-07-07 13:22:34,884 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 13:22:39,061 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.168e+07
2023-07-07 13:22:43,246 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 13:22:47,416 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.291e+07
2023-07-07 13:22:51,610 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 13:22:55,801 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.414e+07
2023-07-07 13:22:59,974 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 13:23:04,179 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 13:23:08,387 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 13:23:12,617 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.659e+07
2023-07-07 13:23:16,833 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 13:23:21,042 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.782e+07
2023-07-07 13:23:25,240 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 13:23:29,443 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.905e+07
2023-07-07 13:23:33,651 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 13:23:37,821 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.028e+07
2023-07-07 13:23:41,995 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 13:23:46,178 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 13:23:50,371 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 13:23:54,559 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=2.274e+07
2023-07-07 13:23:58,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 13:24:02,958 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=2.397e+07
2023-07-07 13:24:07,127 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 13:24:11,289 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=2.520e+07
2023-07-07 13:24:15,461 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 13:24:19,644 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=2.643e+07
2023-07-07 13:24:23,818 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 13:24:27,985 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=2.765e+07
2023-07-07 13:24:32,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 13:24:36,348 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=2.888e+07
2023-07-07 13:24:40,553 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 13:24:44,733 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=3.011e+07
2023-07-07 13:24:48,914 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 13:24:53,087 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=3.134e+07
2023-07-07 13:24:57,248 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 13:25:01,433 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=3.257e+07
2023-07-07 13:25:05,620 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 13:25:09,797 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 13:25:13,966 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 13:25:18,179 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=3.503e+07
2023-07-07 13:25:22,438 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 13:25:26,624 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=3.626e+07
2023-07-07 13:25:30,833 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 13:25:35,050 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=3.748e+07
2023-07-07 13:25:39,254 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=3.810e+07
2023-07-07 13:25:43,439 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=3.871e+07
2023-07-07 13:25:47,623 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 13:25:51,825 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=3.994e+07
2023-07-07 13:25:55,994 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 13:26:00,180 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=4.117e+07
2023-07-07 13:26:04,375 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 13:26:08,562 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=4.240e+07
2023-07-07 13:26:12,750 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=4.301e+07
2023-07-07 13:26:16,928 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=4.363e+07
2023-07-07 13:26:21,126 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7200, best=0.66, avg=0.64, std=0.00, steps=4.424e+07
2023-07-07 13:26:25,312 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7300, best=0.72, avg=0.70, std=0.01, steps=4.486e+07
2023-07-07 13:26:29,536 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=4.547e+07
2023-07-07 13:26:33,760 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7500, best=0.74, avg=0.73, std=0.01, steps=4.609e+07
2023-07-07 13:26:37,972 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7600, best=0.74, avg=0.73, std=0.01, steps=4.670e+07
2023-07-07 13:26:42,184 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7700, best=0.75, avg=0.74, std=0.01, steps=4.731e+07
2023-07-07 13:26:46,406 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7800, best=0.77, avg=0.75, std=0.01, steps=4.793e+07
2023-07-07 13:26:50,615 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 7900, best=0.78, avg=0.76, std=0.01, steps=4.854e+07
2023-07-07 13:26:54,827 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8000, best=0.79, avg=0.77, std=0.01, steps=4.916e+07
2023-07-07 13:26:59,043 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8100, best=0.79, avg=0.77, std=0.01, steps=4.977e+07
2023-07-07 13:27:03,245 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8200, best=0.79, avg=0.78, std=0.01, steps=5.039e+07
2023-07-07 13:27:07,417 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8300, best=0.80, avg=0.79, std=0.01, steps=5.100e+07
2023-07-07 13:27:11,587 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8400, best=0.81, avg=0.79, std=0.01, steps=5.162e+07
2023-07-07 13:27:15,768 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8500, best=0.82, avg=0.80, std=0.01, steps=5.223e+07
2023-07-07 13:27:19,976 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8600, best=0.82, avg=0.81, std=0.01, steps=5.284e+07
2023-07-07 13:27:24,186 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8700, best=0.83, avg=0.81, std=0.01, steps=5.346e+07
2023-07-07 13:27:28,390 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8800, best=0.83, avg=0.81, std=0.00, steps=5.407e+07
2023-07-07 13:27:32,597 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 8900, best=0.83, avg=0.81, std=0.01, steps=5.469e+07
2023-07-07 13:27:36,780 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9000, best=0.84, avg=0.82, std=0.01, steps=5.530e+07
2023-07-07 13:27:41,008 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9100, best=0.84, avg=0.83, std=0.01, steps=5.592e+07
2023-07-07 13:27:45,195 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9200, best=0.85, avg=0.83, std=0.01, steps=5.653e+07
2023-07-07 13:27:49,368 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9300, best=0.85, avg=0.84, std=0.00, steps=5.715e+07
2023-07-07 13:27:53,578 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9400, best=0.86, avg=0.84, std=0.01, steps=5.776e+07
2023-07-07 13:27:57,805 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9500, best=0.85, avg=0.84, std=0.00, steps=5.837e+07
2023-07-07 13:28:01,997 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9600, best=0.86, avg=0.85, std=0.00, steps=5.899e+07
2023-07-07 13:28:06,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9700, best=0.86, avg=0.85, std=0.00, steps=5.960e+07
2023-07-07 13:28:10,347 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9800, best=0.87, avg=0.85, std=0.00, steps=6.022e+07
2023-07-07 13:28:14,541 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 9900, best=0.88, avg=0.86, std=0.00, steps=6.083e+07
2023-07-07 13:28:18,746 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10000, best=0.88, avg=0.86, std=0.00, steps=6.145e+07
2023-07-07 13:28:22,937 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10100, best=0.88, avg=0.87, std=0.00, steps=6.206e+07
2023-07-07 13:28:27,133 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10200, best=0.89, avg=0.88, std=0.00, steps=6.267e+07
2023-07-07 13:28:31,345 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10300, best=0.89, avg=0.88, std=0.00, steps=6.329e+07
2023-07-07 13:28:35,539 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10400, best=0.90, avg=0.89, std=0.00, steps=6.390e+07
2023-07-07 13:28:39,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10500, best=0.90, avg=0.88, std=0.00, steps=6.452e+07
2023-07-07 13:28:43,957 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10600, best=0.90, avg=0.89, std=0.00, steps=6.513e+07
2023-07-07 13:28:48,159 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10700, best=0.90, avg=0.89, std=0.00, steps=6.575e+07
2023-07-07 13:28:52,342 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10800, best=0.90, avg=0.89, std=0.00, steps=6.636e+07
2023-07-07 13:28:56,534 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 10900, best=0.90, avg=0.89, std=0.00, steps=6.698e+07
2023-07-07 13:29:00,737 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11000, best=0.91, avg=0.90, std=0.00, steps=6.759e+07
2023-07-07 13:29:04,952 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11100, best=0.91, avg=0.90, std=0.00, steps=6.820e+07
2023-07-07 13:29:09,181 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11200, best=0.91, avg=0.90, std=0.00, steps=6.882e+07
2023-07-07 13:29:13,390 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11300, best=0.91, avg=0.90, std=0.00, steps=6.943e+07
2023-07-07 13:29:17,592 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11400, best=0.91, avg=0.90, std=0.00, steps=7.005e+07
2023-07-07 13:29:21,790 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11500, best=0.91, avg=0.90, std=0.00, steps=7.066e+07
2023-07-07 13:29:25,949 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11600, best=0.92, avg=0.90, std=0.00, steps=7.128e+07
2023-07-07 13:29:30,158 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11700, best=0.92, avg=0.91, std=0.00, steps=7.189e+07
2023-07-07 13:29:34,413 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11800, best=0.92, avg=0.91, std=0.00, steps=7.251e+07
2023-07-07 13:29:38,590 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11900, best=0.92, avg=0.91, std=0.00, steps=7.312e+07
2023-07-07 13:29:42,744 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 2, [Train]: 11999, best=0.92, avg=0.91, std=0.00, steps=7.373e+07
2023-07-07 13:29:42,744 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:29:42,770 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:29:42,770 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:29:42,801 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:29:49,544 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 13:29:55,014 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 13:30:00,513 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 13:30:06,015 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 13:30:11,501 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 13:30:16,989 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 13:30:22,465 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 13:30:27,928 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 13:30:33,393 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 13:30:38,848 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 13:30:44,354 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=9.019e+06
2023-07-07 13:30:49,876 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 13:30:55,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 13:31:00,835 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 13:31:06,306 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 13:31:11,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 13:31:17,306 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 13:31:22,785 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 13:31:28,271 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 13:31:33,757 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 13:31:39,218 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 13:31:44,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 13:31:50,301 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 13:31:55,770 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 13:32:01,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 13:32:06,693 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 13:32:12,172 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 13:32:17,646 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 13:32:23,133 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 13:32:28,636 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 13:32:34,110 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 13:32:39,588 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 13:32:45,060 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 13:32:50,519 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 13:32:55,985 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 13:33:01,462 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 13:33:06,940 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 13:33:12,418 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 13:33:17,886 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 13:33:23,360 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 13:33:28,833 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 13:33:34,347 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 13:33:39,833 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 13:33:45,332 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 13:33:50,830 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 13:33:56,325 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 13:34:01,784 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 13:34:07,241 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 13:34:12,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 13:34:18,195 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 13:34:23,698 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 13:34:29,204 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 13:34:34,710 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 13:34:40,185 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 13:34:45,670 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 13:34:51,148 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 13:34:56,602 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 13:35:02,054 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 13:35:07,517 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 13:35:12,978 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 13:35:18,481 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 13:35:23,951 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 13:35:29,415 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 13:35:34,928 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 13:35:40,440 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 13:35:45,939 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 13:35:51,467 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 13:35:57,036 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 13:36:02,574 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 13:36:08,079 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 13:36:13,572 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 13:36:19,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 13:36:24,537 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7300, best=0.71, avg=0.69, std=0.01, steps=5.981e+07
2023-07-07 13:36:30,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7400, best=0.72, avg=0.71, std=0.01, steps=6.063e+07
2023-07-07 13:36:35,499 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7500, best=0.73, avg=0.71, std=0.01, steps=6.145e+07
2023-07-07 13:36:41,037 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7600, best=0.73, avg=0.72, std=0.01, steps=6.227e+07
2023-07-07 13:36:46,570 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7700, best=0.73, avg=0.72, std=0.01, steps=6.309e+07
2023-07-07 13:36:52,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7800, best=0.74, avg=0.73, std=0.01, steps=6.391e+07
2023-07-07 13:36:57,570 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 7900, best=0.75, avg=0.73, std=0.01, steps=6.472e+07
2023-07-07 13:37:03,070 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8000, best=0.75, avg=0.74, std=0.01, steps=6.554e+07
2023-07-07 13:37:08,573 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8100, best=0.76, avg=0.75, std=0.01, steps=6.636e+07
2023-07-07 13:37:14,050 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8200, best=0.77, avg=0.76, std=0.00, steps=6.718e+07
2023-07-07 13:37:19,557 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8300, best=0.78, avg=0.77, std=0.01, steps=6.800e+07
2023-07-07 13:37:25,066 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8400, best=0.79, avg=0.78, std=0.01, steps=6.882e+07
2023-07-07 13:37:30,589 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8500, best=0.80, avg=0.78, std=0.01, steps=6.964e+07
2023-07-07 13:37:36,095 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8600, best=0.81, avg=0.79, std=0.01, steps=7.046e+07
2023-07-07 13:37:41,616 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8700, best=0.80, avg=0.79, std=0.01, steps=7.128e+07
2023-07-07 13:37:47,155 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8800, best=0.81, avg=0.80, std=0.01, steps=7.210e+07
2023-07-07 13:37:52,672 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 8900, best=0.82, avg=0.80, std=0.01, steps=7.292e+07
2023-07-07 13:37:58,150 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9000, best=0.82, avg=0.80, std=0.01, steps=7.374e+07
2023-07-07 13:38:03,637 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9100, best=0.82, avg=0.81, std=0.01, steps=7.456e+07
2023-07-07 13:38:09,118 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9200, best=0.83, avg=0.81, std=0.01, steps=7.537e+07
2023-07-07 13:38:14,588 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9300, best=0.83, avg=0.81, std=0.01, steps=7.619e+07
2023-07-07 13:38:20,060 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9400, best=0.83, avg=0.82, std=0.01, steps=7.701e+07
2023-07-07 13:38:25,544 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9500, best=0.84, avg=0.82, std=0.01, steps=7.783e+07
2023-07-07 13:38:31,052 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9600, best=0.84, avg=0.83, std=0.01, steps=7.865e+07
2023-07-07 13:38:36,556 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9700, best=0.84, avg=0.83, std=0.00, steps=7.947e+07
2023-07-07 13:38:42,050 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9800, best=0.84, avg=0.83, std=0.00, steps=8.029e+07
2023-07-07 13:38:47,564 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 9900, best=0.85, avg=0.83, std=0.00, steps=8.111e+07
2023-07-07 13:38:53,107 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10000, best=0.85, avg=0.83, std=0.00, steps=8.193e+07
2023-07-07 13:38:58,612 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10100, best=0.85, avg=0.84, std=0.01, steps=8.275e+07
2023-07-07 13:39:04,121 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10200, best=0.85, avg=0.84, std=0.01, steps=8.357e+07
2023-07-07 13:39:09,615 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10300, best=0.85, avg=0.84, std=0.01, steps=8.439e+07
2023-07-07 13:39:15,115 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10400, best=0.85, avg=0.84, std=0.00, steps=8.520e+07
2023-07-07 13:39:20,606 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10500, best=0.85, avg=0.84, std=0.00, steps=8.602e+07
2023-07-07 13:39:26,102 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10600, best=0.86, avg=0.84, std=0.01, steps=8.684e+07
2023-07-07 13:39:31,594 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10700, best=0.86, avg=0.85, std=0.00, steps=8.766e+07
2023-07-07 13:39:37,072 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10800, best=0.86, avg=0.85, std=0.01, steps=8.848e+07
2023-07-07 13:39:42,543 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 10900, best=0.86, avg=0.85, std=0.00, steps=8.930e+07
2023-07-07 13:39:48,000 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11000, best=0.86, avg=0.85, std=0.00, steps=9.012e+07
2023-07-07 13:39:53,466 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11100, best=0.86, avg=0.85, std=0.00, steps=9.094e+07
2023-07-07 13:39:58,950 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11200, best=0.87, avg=0.85, std=0.00, steps=9.176e+07
2023-07-07 13:40:04,430 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11300, best=0.86, avg=0.86, std=0.00, steps=9.258e+07
2023-07-07 13:40:09,898 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11400, best=0.87, avg=0.86, std=0.00, steps=9.340e+07
2023-07-07 13:40:15,363 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11500, best=0.87, avg=0.86, std=0.00, steps=9.422e+07
2023-07-07 13:40:20,808 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11600, best=0.87, avg=0.86, std=0.00, steps=9.504e+07
2023-07-07 13:40:26,276 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11700, best=0.87, avg=0.86, std=0.00, steps=9.585e+07
2023-07-07 13:40:31,757 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11800, best=0.87, avg=0.86, std=0.00, steps=9.667e+07
2023-07-07 13:40:37,242 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11900, best=0.87, avg=0.86, std=0.00, steps=9.749e+07
2023-07-07 13:40:42,691 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 2, [Train]: 11999, best=0.87, avg=0.86, std=0.00, steps=9.830e+07
2023-07-07 13:40:42,691 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:40:42,717 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:40:42,717 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:40:42,748 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:40:52,070 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 13:41:00,128 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 13:41:08,169 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 13:41:16,198 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 13:41:24,297 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 13:41:32,426 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 13:41:40,483 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 13:41:48,553 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 13:41:56,625 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 13:42:04,668 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 13:42:12,745 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 13:42:20,858 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 13:42:28,899 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.599e+07
2023-07-07 13:42:37,007 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 13:42:45,087 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 13:42:53,169 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 13:43:01,237 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 13:43:09,333 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 13:43:17,419 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 13:43:25,477 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 13:43:33,549 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 13:43:41,633 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=2.705e+07
2023-07-07 13:43:49,687 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 13:43:57,731 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 13:44:05,845 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 13:44:13,919 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 13:44:21,983 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 13:44:30,036 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 13:44:38,084 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 13:44:46,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 13:44:54,217 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 13:45:02,310 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 13:45:10,399 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 13:45:18,477 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 13:45:26,548 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 13:45:34,618 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 13:45:42,718 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3700, best=0.51, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 13:45:50,819 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 13:45:58,883 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 13:46:06,947 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 13:46:15,021 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 13:46:23,086 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 13:46:31,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 13:46:39,229 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 13:46:47,308 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 13:46:55,386 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 13:47:03,450 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 13:47:11,484 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 13:47:19,576 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 13:47:27,663 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 13:47:35,758 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 13:47:43,797 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 13:47:51,859 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=6.514e+07
2023-07-07 13:47:59,965 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5400, best=0.53, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 13:48:08,116 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 13:48:16,243 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 13:48:24,299 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 13:48:32,361 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 13:48:40,444 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 13:48:48,489 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 13:48:56,531 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 13:49:04,629 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 13:49:12,692 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 13:49:20,748 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 13:49:28,805 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 13:49:36,858 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 13:49:44,906 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 13:49:52,954 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 13:50:01,047 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 13:50:09,163 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 13:50:17,204 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 13:50:25,240 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 13:50:33,278 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 13:50:41,394 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 13:50:49,494 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 13:50:57,608 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 13:51:05,717 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7700, best=0.53, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 13:51:13,825 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 13:51:21,906 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 13:51:30,046 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 13:51:38,116 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 13:51:46,156 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 13:51:54,239 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 13:52:02,274 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 13:52:10,373 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 13:52:18,492 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=1.057e+08
2023-07-07 13:52:26,597 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.069e+08
2023-07-07 13:52:34,666 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 13:52:42,736 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=1.094e+08
2023-07-07 13:52:50,790 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.106e+08
2023-07-07 13:52:58,894 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 13:53:07,007 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 13:53:15,120 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=1.143e+08
2023-07-07 13:53:23,219 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=1.155e+08
2023-07-07 13:53:31,354 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=1.167e+08
2023-07-07 13:53:39,503 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 13:53:47,587 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=1.192e+08
2023-07-07 13:53:55,645 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9800, best=0.53, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 13:54:03,744 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=1.217e+08
2023-07-07 13:54:11,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 13:54:19,895 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 13:54:27,960 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.253e+08
2023-07-07 13:54:36,080 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=1.266e+08
2023-07-07 13:54:44,197 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 13:54:52,285 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.290e+08
2023-07-07 13:55:00,394 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=1.303e+08
2023-07-07 13:55:08,535 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10700, best=0.65, avg=0.64, std=0.00, steps=1.315e+08
2023-07-07 13:55:16,620 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10800, best=0.65, avg=0.64, std=0.01, steps=1.327e+08
2023-07-07 13:55:24,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 10900, best=0.64, avg=0.63, std=0.01, steps=1.340e+08
2023-07-07 13:55:32,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11000, best=0.66, avg=0.65, std=0.01, steps=1.352e+08
2023-07-07 13:55:40,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11100, best=0.67, avg=0.66, std=0.00, steps=1.364e+08
2023-07-07 13:55:49,016 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11200, best=0.68, avg=0.67, std=0.01, steps=1.376e+08
2023-07-07 13:55:57,111 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11300, best=0.68, avg=0.67, std=0.01, steps=1.389e+08
2023-07-07 13:56:05,201 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11400, best=0.68, avg=0.67, std=0.01, steps=1.401e+08
2023-07-07 13:56:13,300 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11500, best=0.69, avg=0.67, std=0.01, steps=1.413e+08
2023-07-07 13:56:21,377 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11600, best=0.69, avg=0.67, std=0.01, steps=1.426e+08
2023-07-07 13:56:29,505 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11700, best=0.69, avg=0.68, std=0.01, steps=1.438e+08
2023-07-07 13:56:37,627 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11800, best=0.69, avg=0.68, std=0.01, steps=1.450e+08
2023-07-07 13:56:45,743 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11900, best=0.70, avg=0.68, std=0.01, steps=1.462e+08
2023-07-07 13:56:53,760 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 2, [Train]: 11999, best=0.71, avg=0.69, std=0.01, steps=1.475e+08
2023-07-07 13:56:53,761 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:56:53,788 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:56:53,789 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:56:53,823 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:57:00,550 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 13:57:06,024 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 13:57:11,495 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 13:57:16,965 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 13:57:22,440 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 13:57:27,912 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 13:57:33,367 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 2, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 13:57:37,882 -        meta learning: [    INFO] - KeyboardInterrupt, Begin eval_with_injury.
2023-07-07 13:57:37,882 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:57:37,882 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:57:37,907 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:57:37,907 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:57:37,939 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:57:43,940 -        meta learning: [    INFO] - KeyboardInterrupt, Begin eval_with_injury.
2023-07-07 13:57:43,940 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:57:43,940 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:57:43,962 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:57:43,962 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:57:43,990 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:57:44,558 -        meta learning: [    INFO] - KeyboardInterrupt, Begin eval_with_injury.
2023-07-07 13:57:44,558 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
2023-07-07 13:57:44,559 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-000522
