2023-07-07 13:59:26,680 -        meta learning: [    INFO] - [INFO] checkpoint saved to: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 13:59:26,680 -        meta learning: [    INFO] - [INFO] tensorboard dir set to: ./runs/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 13:59:26,680 -        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=40, num_tests=128, eval_epoch=100, eval=False, eval_with_injury=False, resume='', save=False, repeat=1, root_dir='/data/anonymous/meta', tensorboard_dir='./runs', suffix='', output_dir='/data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926', summary_writer=<torch.utils.tensorboard.writer.SummaryWriter object at 0x7f16987b8d90>, tb_prefix='PGPE/SeqTask/GruPolicy')
2023-07-07 13:59:30,010 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:59:30,011 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:59:30,081 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:59:36,458 -        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 13:59:39,380 -        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 13:59:42,266 -        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 13:59:45,168 -        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 13:59:48,058 -        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 13:59:50,928 -        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 13:59:53,797 -        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 13:59:56,660 -        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 13:59:59,535 -        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 14:00:02,402 -        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 14:00:05,285 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1100, best=0.53, avg=0.50, std=0.01, steps=4.510e+06
2023-07-07 14:00:08,147 -        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 14:00:11,013 -        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 14:00:13,870 -        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 14:00:16,769 -        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 14:00:19,638 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1600, best=0.53, avg=0.50, std=0.01, steps=6.558e+06
2023-07-07 14:00:22,508 -        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 14:00:25,372 -        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 14:00:28,242 -        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 14:00:31,094 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=8.196e+06
2023-07-07 14:00:33,950 -        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 14:00:36,827 -        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 14:00:39,715 -        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 14:00:42,609 -        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 14:00:45,494 -        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 14:00:48,370 -        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 14:00:51,242 -        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 14:00:54,123 -        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 14:00:57,026 -        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 14:00:59,895 -        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 14:01:02,786 -        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 14:01:05,684 -        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 14:01:08,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3300, best=0.53, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 14:01:11,449 -        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 14:01:14,298 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=1.434e+07
2023-07-07 14:01:17,150 -        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 14:01:19,997 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=1.516e+07
2023-07-07 14:01:22,838 -        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 14:01:25,704 -        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 14:01:28,551 -        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 14:01:31,415 -        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 14:01:34,284 -        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 14:01:37,169 -        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 14:01:40,075 -        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 14:01:42,945 -        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 14:01:45,823 -        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 14:01:48,703 -        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 14:01:51,581 -        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 14:01:54,454 -        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 14:01:57,313 -        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 14:02:00,184 -        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 14:02:03,057 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5200, best=0.72, avg=0.71, std=0.01, steps=2.130e+07
2023-07-07 14:02:05,916 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5300, best=0.77, avg=0.75, std=0.01, steps=2.171e+07
2023-07-07 14:02:08,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5400, best=0.79, avg=0.77, std=0.01, steps=2.212e+07
2023-07-07 14:02:11,638 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5500, best=0.82, avg=0.81, std=0.01, steps=2.253e+07
2023-07-07 14:02:14,528 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5600, best=0.84, avg=0.83, std=0.01, steps=2.294e+07
2023-07-07 14:02:17,413 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5700, best=0.86, avg=0.84, std=0.01, steps=2.335e+07
2023-07-07 14:02:20,313 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5800, best=0.87, avg=0.86, std=0.01, steps=2.376e+07
2023-07-07 14:02:23,205 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5900, best=0.89, avg=0.88, std=0.01, steps=2.417e+07
2023-07-07 14:02:26,096 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6000, best=0.90, avg=0.89, std=0.01, steps=2.458e+07
2023-07-07 14:02:28,956 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6100, best=0.91, avg=0.90, std=0.00, steps=2.499e+07
2023-07-07 14:02:31,825 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6200, best=0.91, avg=0.90, std=0.00, steps=2.540e+07
2023-07-07 14:02:34,715 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6300, best=0.92, avg=0.91, std=0.00, steps=2.581e+07
2023-07-07 14:02:37,588 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6400, best=0.93, avg=0.92, std=0.00, steps=2.622e+07
2023-07-07 14:02:40,447 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6500, best=0.94, avg=0.93, std=0.00, steps=2.663e+07
2023-07-07 14:02:43,307 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6600, best=0.95, avg=0.94, std=0.00, steps=2.704e+07
2023-07-07 14:02:46,177 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6700, best=0.96, avg=0.95, std=0.00, steps=2.745e+07
2023-07-07 14:02:49,049 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6800, best=0.96, avg=0.95, std=0.00, steps=2.786e+07
2023-07-07 14:02:51,919 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6900, best=0.96, avg=0.95, std=0.00, steps=2.827e+07
2023-07-07 14:02:54,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7000, best=0.96, avg=0.95, std=0.00, steps=2.868e+07
2023-07-07 14:02:57,634 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7100, best=0.96, avg=0.95, std=0.00, steps=2.909e+07
2023-07-07 14:03:00,515 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7200, best=0.96, avg=0.95, std=0.00, steps=2.950e+07
2023-07-07 14:03:03,403 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7300, best=0.96, avg=0.95, std=0.00, steps=2.990e+07
2023-07-07 14:03:06,298 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7400, best=0.96, avg=0.95, std=0.00, steps=3.031e+07
2023-07-07 14:03:09,177 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7500, best=0.96, avg=0.95, std=0.00, steps=3.072e+07
2023-07-07 14:03:12,053 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7600, best=0.96, avg=0.95, std=0.00, steps=3.113e+07
2023-07-07 14:03:14,933 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7700, best=0.96, avg=0.95, std=0.00, steps=3.154e+07
2023-07-07 14:03:17,819 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7800, best=0.96, avg=0.95, std=0.00, steps=3.195e+07
2023-07-07 14:03:20,696 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7900, best=0.96, avg=0.95, std=0.00, steps=3.236e+07
2023-07-07 14:03:23,570 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8000, best=0.96, avg=0.95, std=0.00, steps=3.277e+07
2023-07-07 14:03:26,441 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8100, best=0.96, avg=0.95, std=0.00, steps=3.318e+07
2023-07-07 14:03:29,307 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8200, best=0.96, avg=0.95, std=0.00, steps=3.359e+07
2023-07-07 14:03:32,179 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8300, best=0.96, avg=0.95, std=0.00, steps=3.400e+07
2023-07-07 14:03:35,052 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8400, best=0.96, avg=0.95, std=0.00, steps=3.441e+07
2023-07-07 14:03:37,933 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8500, best=0.96, avg=0.95, std=0.00, steps=3.482e+07
2023-07-07 14:03:40,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8600, best=0.96, avg=0.95, std=0.00, steps=3.523e+07
2023-07-07 14:03:43,695 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8700, best=0.96, avg=0.95, std=0.00, steps=3.564e+07
2023-07-07 14:03:46,575 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8800, best=0.96, avg=0.95, std=0.00, steps=3.605e+07
2023-07-07 14:03:49,472 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8900, best=0.96, avg=0.95, std=0.00, steps=3.646e+07
2023-07-07 14:03:52,348 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9000, best=0.96, avg=0.95, std=0.00, steps=3.687e+07
2023-07-07 14:03:55,252 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9100, best=0.96, avg=0.95, std=0.00, steps=3.728e+07
2023-07-07 14:03:58,137 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9200, best=0.96, avg=0.95, std=0.00, steps=3.769e+07
2023-07-07 14:04:01,013 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9300, best=0.96, avg=0.95, std=0.00, steps=3.810e+07
2023-07-07 14:04:03,875 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9400, best=0.96, avg=0.95, std=0.00, steps=3.851e+07
2023-07-07 14:04:06,729 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9500, best=0.96, avg=0.95, std=0.00, steps=3.892e+07
2023-07-07 14:04:09,590 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9600, best=0.96, avg=0.95, std=0.00, steps=3.933e+07
2023-07-07 14:04:12,451 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9700, best=0.96, avg=0.95, std=0.00, steps=3.974e+07
2023-07-07 14:04:15,316 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9800, best=0.96, avg=0.95, std=0.00, steps=4.014e+07
2023-07-07 14:04:18,179 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9900, best=0.96, avg=0.95, std=0.00, steps=4.055e+07
2023-07-07 14:04:21,044 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10000, best=0.96, avg=0.95, std=0.00, steps=4.096e+07
2023-07-07 14:04:23,904 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10100, best=0.96, avg=0.95, std=0.00, steps=4.137e+07
2023-07-07 14:04:26,789 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10200, best=0.96, avg=0.95, std=0.00, steps=4.178e+07
2023-07-07 14:04:29,659 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10300, best=0.96, avg=0.95, std=0.00, steps=4.219e+07
2023-07-07 14:04:32,544 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10400, best=0.96, avg=0.95, std=0.00, steps=4.260e+07
2023-07-07 14:04:35,402 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10500, best=0.96, avg=0.95, std=0.00, steps=4.301e+07
2023-07-07 14:04:38,271 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10600, best=0.96, avg=0.95, std=0.00, steps=4.342e+07
2023-07-07 14:04:41,162 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10700, best=0.96, avg=0.95, std=0.00, steps=4.383e+07
2023-07-07 14:04:44,045 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10800, best=0.96, avg=0.95, std=0.00, steps=4.424e+07
2023-07-07 14:04:46,909 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10900, best=0.96, avg=0.95, std=0.00, steps=4.465e+07
2023-07-07 14:04:49,786 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11000, best=0.96, avg=0.95, std=0.00, steps=4.506e+07
2023-07-07 14:04:52,658 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11100, best=0.96, avg=0.95, std=0.00, steps=4.547e+07
2023-07-07 14:04:55,548 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11200, best=0.96, avg=0.95, std=0.00, steps=4.588e+07
2023-07-07 14:04:58,430 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11300, best=0.96, avg=0.95, std=0.00, steps=4.629e+07
2023-07-07 14:05:01,304 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11400, best=0.96, avg=0.95, std=0.00, steps=4.670e+07
2023-07-07 14:05:04,199 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11500, best=0.96, avg=0.95, std=0.00, steps=4.711e+07
2023-07-07 14:05:07,074 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11600, best=0.96, avg=0.95, std=0.00, steps=4.752e+07
2023-07-07 14:05:09,940 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11700, best=0.96, avg=0.95, std=0.00, steps=4.793e+07
2023-07-07 14:05:12,804 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11800, best=0.96, avg=0.95, std=0.00, steps=4.834e+07
2023-07-07 14:05:15,662 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11900, best=0.96, avg=0.95, std=0.00, steps=4.875e+07
2023-07-07 14:05:18,502 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11999, best=0.96, avg=0.95, std=0.00, steps=4.915e+07
2023-07-07 14:05:18,503 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 14:05:18,528 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:05:18,528 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:05:18,558 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:05:24,250 -        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 14:05:28,427 -        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 14:05:32,564 -        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 14:05:36,708 -        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 14:05:40,867 -        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 14:05:45,024 -        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 14:05:49,183 -        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 14:05:53,337 -        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 14:05:57,491 -        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 14:06:01,659 -        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 14:06:05,820 -        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 14:06:09,965 -        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 14:06:14,117 -        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 14:06:18,268 -        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 14:06:22,410 -        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 14:06:26,564 -        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 14:06:30,735 -        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 14:06:34,935 -        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 14:06:39,095 -        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 14:06:43,268 -        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 14:06:47,431 -        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 14:06:51,593 -        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 14:06:55,756 -        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 14:06:59,909 -        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 14:07:04,062 -        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 14:07:08,216 -        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 14:07:12,379 -        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 14:07:16,545 -        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 14:07:20,718 -        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 14:07:24,881 -        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 14:07:29,041 -        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 14:07:33,206 -        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 14:07:37,366 -        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 14:07:41,544 -        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 14:07:45,713 -        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 14:07:49,916 -        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 14:07:54,078 -        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 14:07:58,225 -        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 14:08:02,383 -        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 14:08:06,527 -        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 14:08:10,687 -        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 14:08:14,832 -        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 14:08:18,984 -        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 14:08:23,146 -        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 14:08:27,311 -        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 14:08:31,474 -        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 14:08:35,620 -        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 14:08:39,756 -        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 14:08:43,901 -        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 14:08:48,019 -        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 14:08:52,154 -        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 14:08:56,291 -        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 14:09:00,429 -        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 14:09:04,575 -        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 14:09:08,720 -        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 14:09:12,872 -        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 14:09:17,031 -        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 14:09:21,194 -        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 14:09:25,349 -        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 14:09:29,502 -        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 14:09:33,661 -        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 14:09:37,819 -        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 14:09:41,985 -        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 14:09:46,143 -        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 14:09:50,293 -        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 14:09:54,456 -        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 14:09:58,615 -        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 14:10:02,790 -        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 14:10:06,970 -        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 14:10:11,153 -        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 14:10:15,319 -        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 14:10:19,482 -        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 14:10:23,633 -        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 14:10:27,785 -        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 14:10:31,926 -        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 14:10:36,080 -        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 14:10:40,255 -        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 14:10:44,424 -        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 14:10:48,588 -        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 14:10:52,733 -        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 14:10:56,879 -        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 14:11:01,031 -        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 14:11:05,196 -        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 14:11:09,350 -        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 14:11:13,513 -        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 14:11:17,662 -        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 14:11:21,829 -        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 14:11:25,976 -        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 14:11:30,120 -        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 14:11:34,274 -        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 14:11:38,427 -        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 14:11:42,586 -        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 14:11:46,747 -        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 14:11:50,923 -        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 14:11:55,095 -        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 14:11:59,269 -        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 14:12:03,429 -        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 14:12:07,588 -        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 14:12:11,756 -        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 14:12:15,909 -        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 14:12:20,061 -        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 14:12:24,239 -        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 14:12:28,398 -        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 14:12:32,557 -        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 14:12:36,716 -        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 14:12:40,876 -        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 14:12:45,025 -        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 14:12:49,168 -        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 14:12:53,315 -        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 14:12:57,479 -        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 14:13:01,639 -        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 14:13:05,801 -        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 14:13:09,955 -        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 14:13:14,125 -        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 14:13:18,296 -        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 14:13:22,453 -        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 14:13:26,586 -        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 14:13:30,739 -        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 14:13:34,918 -        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 14:13:39,028 -        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 14:13:39,029 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 14:13:39,054 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:13:39,055 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:13:39,087 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:13:46,161 -        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 14:13:51,616 -        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 14:13:57,059 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 300, best=0.51, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 14:14:02,484 -        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 14:14:07,920 -        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 14:14:13,370 -        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 14:14:18,800 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 700, best=0.53, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 14:14:24,237 -        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 14:14:29,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 900, best=0.53, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 14:14:35,132 -        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 14:14:40,578 -        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 14:14:46,024 -        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 14:14:51,453 -        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 14:14:56,895 -        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 14:15:02,337 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1500, best=0.53, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:15:07,793 -        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 14:15:13,232 -        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 14:15:18,660 -        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 14:15:24,087 -        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 14:15:29,522 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 14:15:34,958 -        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 14:15:40,396 -        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 14:15:45,829 -        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 14:15:51,277 -        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 14:15:56,708 -        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 14:16:02,142 -        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 14:16:07,575 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2700, best=0.53, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 14:16:13,034 -        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 14:16:18,495 -        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 14:16:23,944 -        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 14:16:29,361 -        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 14:16:34,814 -        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 14:16:40,244 -        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 14:16:45,696 -        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 14:16:51,136 -        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 14:16:56,577 -        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 14:17:02,038 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 14:17:07,494 -        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 14:17:12,928 -        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 14:17:18,352 -        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 14:17:23,792 -        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 14:17:29,243 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4200, best=0.53, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 14:17:34,693 -        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 14:17:40,154 -        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 14:17:45,621 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4500, best=0.53, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:17:51,076 -        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 14:17:56,544 -        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 14:18:01,993 -        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 14:18:07,422 -        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 14:18:12,853 -        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 14:18:18,289 -        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 14:18:23,740 -        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 14:18:29,198 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5300, best=0.53, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 14:18:34,658 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5400, best=0.68, avg=0.67, std=0.00, steps=4.424e+07
2023-07-07 14:18:40,094 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5500, best=0.71, avg=0.69, std=0.01, steps=4.506e+07
2023-07-07 14:18:45,558 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5600, best=0.71, avg=0.70, std=0.00, steps=4.588e+07
2023-07-07 14:18:51,012 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5700, best=0.71, avg=0.70, std=0.01, steps=4.670e+07
2023-07-07 14:18:56,481 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5800, best=0.72, avg=0.71, std=0.01, steps=4.752e+07
2023-07-07 14:19:01,933 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5900, best=0.73, avg=0.71, std=0.01, steps=4.834e+07
2023-07-07 14:19:07,407 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6000, best=0.74, avg=0.72, std=0.01, steps=4.916e+07
2023-07-07 14:19:12,853 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6100, best=0.73, avg=0.72, std=0.01, steps=4.998e+07
2023-07-07 14:19:18,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6200, best=0.73, avg=0.72, std=0.01, steps=5.080e+07
2023-07-07 14:19:23,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6300, best=0.75, avg=0.72, std=0.01, steps=5.162e+07
2023-07-07 14:19:29,197 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6400, best=0.75, avg=0.73, std=0.01, steps=5.244e+07
2023-07-07 14:19:34,632 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6500, best=0.75, avg=0.74, std=0.01, steps=5.326e+07
2023-07-07 14:19:40,076 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6600, best=0.75, avg=0.74, std=0.00, steps=5.408e+07
2023-07-07 14:19:45,516 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6700, best=0.76, avg=0.75, std=0.01, steps=5.489e+07
2023-07-07 14:19:50,946 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6800, best=0.77, avg=0.76, std=0.01, steps=5.571e+07
2023-07-07 14:19:56,403 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6900, best=0.78, avg=0.76, std=0.01, steps=5.653e+07
2023-07-07 14:20:01,856 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7000, best=0.79, avg=0.77, std=0.01, steps=5.735e+07
2023-07-07 14:20:07,316 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7100, best=0.78, avg=0.77, std=0.01, steps=5.817e+07
2023-07-07 14:20:12,766 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7200, best=0.80, avg=0.78, std=0.01, steps=5.899e+07
2023-07-07 14:20:18,222 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7300, best=0.80, avg=0.79, std=0.01, steps=5.981e+07
2023-07-07 14:20:23,677 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7400, best=0.81, avg=0.79, std=0.01, steps=6.063e+07
2023-07-07 14:20:29,120 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7500, best=0.81, avg=0.79, std=0.01, steps=6.145e+07
2023-07-07 14:20:34,576 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7600, best=0.81, avg=0.80, std=0.01, steps=6.227e+07
2023-07-07 14:20:40,026 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7700, best=0.82, avg=0.80, std=0.01, steps=6.309e+07
2023-07-07 14:20:45,457 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7800, best=0.82, avg=0.81, std=0.01, steps=6.391e+07
2023-07-07 14:20:50,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7900, best=0.83, avg=0.81, std=0.01, steps=6.472e+07
2023-07-07 14:20:56,321 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8000, best=0.83, avg=0.82, std=0.01, steps=6.554e+07
2023-07-07 14:21:01,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8100, best=0.83, avg=0.82, std=0.01, steps=6.636e+07
2023-07-07 14:21:07,204 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8200, best=0.84, avg=0.82, std=0.01, steps=6.718e+07
2023-07-07 14:21:12,718 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8300, best=0.85, avg=0.84, std=0.01, steps=6.800e+07
2023-07-07 14:21:18,159 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8400, best=0.85, avg=0.84, std=0.01, steps=6.882e+07
2023-07-07 14:21:23,591 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8500, best=0.85, avg=0.84, std=0.00, steps=6.964e+07
2023-07-07 14:21:29,029 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8600, best=0.86, avg=0.85, std=0.00, steps=7.046e+07
2023-07-07 14:21:34,479 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8700, best=0.86, avg=0.85, std=0.00, steps=7.128e+07
2023-07-07 14:21:39,942 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8800, best=0.86, avg=0.85, std=0.00, steps=7.210e+07
2023-07-07 14:21:45,400 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8900, best=0.87, avg=0.86, std=0.00, steps=7.292e+07
2023-07-07 14:21:50,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9000, best=0.87, avg=0.86, std=0.00, steps=7.374e+07
2023-07-07 14:21:56,234 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9100, best=0.87, avg=0.86, std=0.00, steps=7.456e+07
2023-07-07 14:22:01,678 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9200, best=0.87, avg=0.86, std=0.00, steps=7.537e+07
2023-07-07 14:22:07,126 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9300, best=0.88, avg=0.86, std=0.00, steps=7.619e+07
2023-07-07 14:22:12,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9400, best=0.88, avg=0.86, std=0.00, steps=7.701e+07
2023-07-07 14:22:18,024 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9500, best=0.88, avg=0.86, std=0.00, steps=7.783e+07
2023-07-07 14:22:23,462 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9600, best=0.88, avg=0.87, std=0.00, steps=7.865e+07
2023-07-07 14:22:28,895 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9700, best=0.88, avg=0.87, std=0.00, steps=7.947e+07
2023-07-07 14:22:34,321 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9800, best=0.88, avg=0.87, std=0.00, steps=8.029e+07
2023-07-07 14:22:39,750 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9900, best=0.88, avg=0.87, std=0.00, steps=8.111e+07
2023-07-07 14:22:45,176 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10000, best=0.88, avg=0.87, std=0.00, steps=8.193e+07
2023-07-07 14:22:50,605 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10100, best=0.89, avg=0.87, std=0.00, steps=8.275e+07
2023-07-07 14:22:56,029 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10200, best=0.89, avg=0.87, std=0.00, steps=8.357e+07
2023-07-07 14:23:01,456 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10300, best=0.89, avg=0.88, std=0.00, steps=8.439e+07
2023-07-07 14:23:06,892 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10400, best=0.89, avg=0.88, std=0.00, steps=8.520e+07
2023-07-07 14:23:12,351 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10500, best=0.89, avg=0.88, std=0.00, steps=8.602e+07
2023-07-07 14:23:17,840 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10600, best=0.89, avg=0.88, std=0.00, steps=8.684e+07
2023-07-07 14:23:23,295 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10700, best=0.89, avg=0.88, std=0.00, steps=8.766e+07
2023-07-07 14:23:28,745 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10800, best=0.89, avg=0.88, std=0.00, steps=8.848e+07
2023-07-07 14:23:34,207 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10900, best=0.89, avg=0.88, std=0.00, steps=8.930e+07
2023-07-07 14:23:39,654 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11000, best=0.89, avg=0.88, std=0.00, steps=9.012e+07
2023-07-07 14:23:45,101 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11100, best=0.89, avg=0.88, std=0.00, steps=9.094e+07
2023-07-07 14:23:50,561 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11200, best=0.89, avg=0.88, std=0.00, steps=9.176e+07
2023-07-07 14:23:55,998 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11300, best=0.89, avg=0.88, std=0.00, steps=9.258e+07
2023-07-07 14:24:01,442 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11400, best=0.89, avg=0.88, std=0.00, steps=9.340e+07
2023-07-07 14:24:06,865 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11500, best=0.89, avg=0.88, std=0.00, steps=9.422e+07
2023-07-07 14:24:12,315 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11600, best=0.89, avg=0.88, std=0.00, steps=9.504e+07
2023-07-07 14:24:17,775 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11700, best=0.89, avg=0.88, std=0.00, steps=9.585e+07
2023-07-07 14:24:23,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11800, best=0.89, avg=0.88, std=0.00, steps=9.667e+07
2023-07-07 14:24:28,658 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11900, best=0.89, avg=0.88, std=0.00, steps=9.749e+07
2023-07-07 14:24:34,044 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11999, best=0.90, avg=0.88, std=0.00, steps=9.830e+07
2023-07-07 14:24:34,044 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 14:24:34,073 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:24:34,073 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:24:34,109 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:24:43,751 -        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 14:24:51,774 -        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 14:24:59,815 -        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 14:25:07,806 -        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 14:25:15,806 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 500, best=0.53, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 14:25:23,806 -        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 14:25:31,814 -        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 14:25:39,814 -        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 14:25:47,822 -        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 14:25:55,812 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1000, best=0.53, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:26:03,848 -        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 14:26:11,830 -        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 14:26:19,821 -        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 14:26:27,821 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 14:26:35,838 -        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 14:26:43,847 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 14:26:51,836 -        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 14:26:59,838 -        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 14:27:07,838 -        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 14:27:15,843 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 14:27:23,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2100, best=0.53, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 14:27:31,803 -        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 14:27:39,795 -        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 14:27:47,779 -        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 14:27:55,769 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2500, best=0.53, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 14:28:03,766 -        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 14:28:11,756 -        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 14:28:19,780 -        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 14:28:27,765 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 14:28:35,750 -        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 14:28:43,771 -        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 14:28:51,782 -        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 14:28:59,791 -        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 14:29:07,801 -        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 14:29:15,808 -        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 14:29:23,820 -        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 14:29:31,843 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=4.548e+07
2023-07-07 14:29:39,864 -        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 14:29:47,868 -        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 14:29:55,874 -        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 14:30:03,877 -        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 14:30:11,889 -        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 14:30:19,893 -        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 14:30:27,882 -        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 14:30:35,891 -        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 14:30:43,888 -        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 14:30:51,911 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4700, best=0.53, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 14:30:59,927 -        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 14:31:07,959 -        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 14:31:15,972 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5000, best=0.53, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:31:23,960 -        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 14:31:31,976 -        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 14:31:39,990 -        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 14:31:47,977 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 14:31:55,972 -        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 14:32:03,962 -        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 14:32:11,960 -        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 14:32:19,962 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 14:32:27,971 -        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 14:32:35,971 -        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 14:32:43,983 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6100, best=0.53, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 14:32:51,986 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 14:33:00,004 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6300, best=0.53, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 14:33:08,006 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 14:33:16,036 -        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 14:33:24,045 -        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 14:33:32,060 -        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 14:33:40,073 -        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 14:33:48,079 -        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 14:33:56,110 -        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 14:34:04,120 -        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 14:34:12,154 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 14:34:20,154 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 14:34:28,163 -        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 14:34:36,169 -        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 14:34:44,192 -        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 14:34:52,207 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 14:35:00,224 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7800, best=0.53, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 14:35:08,248 -        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 14:35:16,262 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 14:35:24,265 -        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 14:35:32,263 -        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 14:35:40,265 -        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 14:35:48,280 -        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 14:35:56,294 -        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 14:36:04,295 -        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 14:36:12,309 -        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 14:36:20,325 -        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 14:36:28,338 -        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 14:36:36,350 -        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 14:36:44,388 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9100, best=0.53, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 14:36:52,404 -        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 14:37:00,388 -        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 14:37:08,382 -        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 14:37:16,385 -        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 14:37:24,392 -        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 14:37:32,382 -        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 14:37:40,386 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 14:37:48,398 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9900, best=0.53, avg=0.50, std=0.01, steps=1.217e+08
2023-07-07 14:37:56,424 -        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 14:38:04,443 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 14:38:12,440 -        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 14:38:20,447 -        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 14:38:28,463 -        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 14:38:36,476 -        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 14:38:44,493 -        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 14:38:52,505 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10700, best=0.65, avg=0.64, std=0.01, steps=1.315e+08
2023-07-07 14:39:00,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10800, best=0.65, avg=0.64, std=0.00, steps=1.327e+08
2023-07-07 14:39:08,533 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10900, best=0.66, avg=0.65, std=0.01, steps=1.340e+08
2023-07-07 14:39:16,550 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11000, best=0.68, avg=0.66, std=0.00, steps=1.352e+08
2023-07-07 14:39:24,586 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11100, best=0.69, avg=0.67, std=0.00, steps=1.364e+08
2023-07-07 14:39:32,603 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11200, best=0.69, avg=0.68, std=0.01, steps=1.376e+08
2023-07-07 14:39:40,611 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11300, best=0.69, avg=0.67, std=0.01, steps=1.389e+08
2023-07-07 14:39:48,608 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11400, best=0.69, avg=0.68, std=0.01, steps=1.401e+08
2023-07-07 14:39:56,596 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11500, best=0.70, avg=0.68, std=0.01, steps=1.413e+08
2023-07-07 14:40:04,583 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11600, best=0.70, avg=0.68, std=0.01, steps=1.426e+08
2023-07-07 14:40:12,563 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11700, best=0.70, avg=0.68, std=0.01, steps=1.438e+08
2023-07-07 14:40:20,545 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11800, best=0.70, avg=0.69, std=0.01, steps=1.450e+08
2023-07-07 14:40:28,527 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11900, best=0.72, avg=0.70, std=0.01, steps=1.462e+08
2023-07-07 14:40:36,437 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11999, best=0.71, avg=0.70, std=0.01, steps=1.475e+08
2023-07-07 14:40:36,438 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 14:40:36,463 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:40:36,463 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:40:36,495 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:40:43,472 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=8.274e+05
2023-07-07 14:40:48,917 -        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 14:40:54,371 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 300, best=0.51, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 14:40:59,802 -        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 14:41:05,237 -        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 14:41:10,677 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=4.923e+06
2023-07-07 14:41:16,108 -        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 14:41:21,527 -        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 14:41:26,965 -        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 14:41:32,386 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 14:41:37,823 -        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 14:41:43,248 -        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 14:41:48,669 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 14:41:54,093 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 14:41:59,520 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:42:04,945 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 14:42:10,376 -        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 14:42:15,817 -        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 14:42:21,254 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 14:42:26,684 -        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 14:42:32,132 -        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 14:42:37,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 14:42:43,018 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=1.885e+07
2023-07-07 14:42:48,458 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=1.967e+07
2023-07-07 14:42:53,896 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 14:42:59,336 -        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 14:43:04,786 -        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 14:43:10,230 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 14:43:15,670 -        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 14:43:21,105 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.00, steps=2.458e+07
2023-07-07 14:43:26,530 -        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 14:43:31,958 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 14:43:37,437 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 14:43:42,910 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 14:43:48,337 -        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 14:43:53,756 -        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 14:43:59,175 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=3.032e+07
2023-07-07 14:44:04,609 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 14:44:10,033 -        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 14:44:15,475 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:44:20,922 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 14:44:26,367 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 14:44:31,818 -        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 14:44:37,261 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.01, steps=3.605e+07
2023-07-07 14:44:42,687 -        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 14:44:48,125 -        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 14:44:53,557 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 14:44:58,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.00, steps=3.933e+07
2023-07-07 14:45:04,427 -        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 14:45:09,881 -        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 14:45:15,330 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 14:45:20,768 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 14:45:26,211 -        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 14:45:31,633 -        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 14:45:37,073 -        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 14:45:42,512 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 14:45:47,960 -        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 14:45:53,384 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 14:45:58,829 -        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 14:46:04,265 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.00, steps=4.916e+07
2023-07-07 14:46:09,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 14:46:15,124 -        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 14:46:20,556 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:46:25,994 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 14:46:31,417 -        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 14:46:36,836 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6600, best=0.62, avg=0.62, std=0.00, steps=5.408e+07
2023-07-07 14:46:42,288 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6700, best=0.69, avg=0.68, std=0.00, steps=5.489e+07
2023-07-07 14:46:47,742 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6800, best=0.71, avg=0.70, std=0.00, steps=5.571e+07
2023-07-07 14:46:53,186 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6900, best=0.73, avg=0.71, std=0.00, steps=5.653e+07
2023-07-07 14:46:58,628 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7000, best=0.74, avg=0.73, std=0.00, steps=5.735e+07
2023-07-07 14:47:04,084 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7100, best=0.74, avg=0.73, std=0.00, steps=5.817e+07
2023-07-07 14:47:09,512 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7200, best=0.75, avg=0.74, std=0.00, steps=5.899e+07
2023-07-07 14:47:14,963 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7300, best=0.76, avg=0.74, std=0.00, steps=5.981e+07
2023-07-07 14:47:20,416 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7400, best=0.76, avg=0.75, std=0.00, steps=6.063e+07
2023-07-07 14:47:25,857 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7500, best=0.77, avg=0.76, std=0.00, steps=6.145e+07
2023-07-07 14:47:31,304 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7600, best=0.78, avg=0.76, std=0.00, steps=6.227e+07
2023-07-07 14:47:36,732 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7700, best=0.78, avg=0.77, std=0.00, steps=6.309e+07
2023-07-07 14:47:42,158 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7800, best=0.79, avg=0.77, std=0.00, steps=6.391e+07
2023-07-07 14:47:47,582 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7900, best=0.79, avg=0.78, std=0.00, steps=6.472e+07
2023-07-07 14:47:53,036 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8000, best=0.80, avg=0.79, std=0.00, steps=6.554e+07
2023-07-07 14:47:58,468 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8100, best=0.81, avg=0.80, std=0.00, steps=6.636e+07
2023-07-07 14:48:03,908 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8200, best=0.82, avg=0.81, std=0.00, steps=6.718e+07
2023-07-07 14:48:09,343 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8300, best=0.83, avg=0.81, std=0.00, steps=6.800e+07
2023-07-07 14:48:14,779 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8400, best=0.83, avg=0.82, std=0.00, steps=6.882e+07
2023-07-07 14:48:20,214 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8500, best=0.84, avg=0.83, std=0.00, steps=6.964e+07
2023-07-07 14:48:25,646 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8600, best=0.84, avg=0.83, std=0.00, steps=7.046e+07
2023-07-07 14:48:31,069 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8700, best=0.84, avg=0.84, std=0.00, steps=7.128e+07
2023-07-07 14:48:36,511 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8800, best=0.85, avg=0.84, std=0.00, steps=7.210e+07
2023-07-07 14:48:41,941 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8900, best=0.86, avg=0.84, std=0.00, steps=7.292e+07
2023-07-07 14:48:47,397 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9000, best=0.86, avg=0.85, std=0.00, steps=7.374e+07
2023-07-07 14:48:52,837 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9100, best=0.86, avg=0.85, std=0.00, steps=7.456e+07
2023-07-07 14:48:58,277 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9200, best=0.87, avg=0.86, std=0.00, steps=7.537e+07
2023-07-07 14:49:03,715 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9300, best=0.87, avg=0.86, std=0.00, steps=7.619e+07
2023-07-07 14:49:09,134 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9400, best=0.87, avg=0.86, std=0.00, steps=7.701e+07
2023-07-07 14:49:14,558 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9500, best=0.88, avg=0.87, std=0.00, steps=7.783e+07
2023-07-07 14:49:19,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9600, best=0.88, avg=0.87, std=0.00, steps=7.865e+07
2023-07-07 14:49:25,418 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9700, best=0.88, avg=0.87, std=0.00, steps=7.947e+07
2023-07-07 14:49:30,845 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9800, best=0.88, avg=0.87, std=0.00, steps=8.029e+07
2023-07-07 14:49:36,279 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9900, best=0.88, avg=0.88, std=0.00, steps=8.111e+07
2023-07-07 14:49:41,724 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10000, best=0.89, avg=0.88, std=0.00, steps=8.193e+07
2023-07-07 14:49:47,164 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10100, best=0.89, avg=0.88, std=0.00, steps=8.275e+07
2023-07-07 14:49:52,588 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10200, best=0.89, avg=0.88, std=0.00, steps=8.357e+07
2023-07-07 14:49:58,030 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10300, best=0.89, avg=0.88, std=0.00, steps=8.439e+07
2023-07-07 14:50:03,476 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10400, best=0.89, avg=0.89, std=0.00, steps=8.520e+07
2023-07-07 14:50:08,899 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10500, best=0.90, avg=0.89, std=0.00, steps=8.602e+07
2023-07-07 14:50:14,321 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10600, best=0.90, avg=0.89, std=0.00, steps=8.684e+07
2023-07-07 14:50:19,770 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10700, best=0.90, avg=0.89, std=0.00, steps=8.766e+07
2023-07-07 14:50:25,227 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10800, best=0.90, avg=0.89, std=0.00, steps=8.848e+07
2023-07-07 14:50:30,664 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10900, best=0.90, avg=0.89, std=0.00, steps=8.930e+07
2023-07-07 14:50:36,102 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11000, best=0.90, avg=0.89, std=0.00, steps=9.012e+07
2023-07-07 14:50:41,529 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11100, best=0.90, avg=0.90, std=0.00, steps=9.094e+07
2023-07-07 14:50:46,956 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11200, best=0.91, avg=0.90, std=0.00, steps=9.176e+07
2023-07-07 14:50:52,417 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11300, best=0.91, avg=0.90, std=0.00, steps=9.258e+07
2023-07-07 14:50:57,850 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11400, best=0.91, avg=0.90, std=0.00, steps=9.340e+07
2023-07-07 14:51:03,281 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11500, best=0.91, avg=0.90, std=0.00, steps=9.422e+07
2023-07-07 14:51:08,694 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11600, best=0.91, avg=0.90, std=0.00, steps=9.504e+07
2023-07-07 14:51:14,126 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11700, best=0.91, avg=0.90, std=0.00, steps=9.585e+07
2023-07-07 14:51:19,557 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11800, best=0.91, avg=0.90, std=0.00, steps=9.667e+07
2023-07-07 14:51:25,001 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11900, best=0.91, avg=0.90, std=0.00, steps=9.749e+07
2023-07-07 14:51:30,369 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11999, best=0.91, avg=0.90, std=0.00, steps=9.830e+07
2023-07-07 14:51:30,370 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 14:51:30,394 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:51:30,394 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:51:30,426 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:51:38,685 -        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 14:51:45,388 -        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 14:51:52,098 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 300, best=0.51, avg=0.50, std=0.01, steps=3.082e+06
2023-07-07 14:51:58,795 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=4.106e+06
2023-07-07 14:52:05,510 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=5.130e+06
2023-07-07 14:52:12,225 -        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 14:52:18,935 -        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 14:52:25,672 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=8.202e+06
2023-07-07 14:52:32,391 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 900, best=0.52, avg=0.50, std=0.00, steps=9.226e+06
2023-07-07 14:52:39,103 -        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 14:52:45,824 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.00, steps=1.127e+07
2023-07-07 14:52:52,533 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:52:59,234 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=1.332e+07
2023-07-07 14:53:05,936 -        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 14:53:12,642 -        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 14:53:19,347 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 14:53:26,053 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=1.742e+07
2023-07-07 14:53:32,759 -        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 14:53:39,483 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.01, steps=1.947e+07
2023-07-07 14:53:46,216 -        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 14:53:52,924 -        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 14:53:59,641 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=2.254e+07
2023-07-07 14:54:06,375 -        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 14:54:13,106 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 14:54:19,835 -        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 14:54:26,546 -        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 14:54:33,267 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.01, steps=2.766e+07
2023-07-07 14:54:39,969 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 14:54:46,684 -        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 14:54:53,413 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 14:55:00,122 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=3.175e+07
2023-07-07 14:55:06,826 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=3.278e+07
2023-07-07 14:55:13,553 -        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 14:55:20,289 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=3.483e+07
2023-07-07 14:55:26,997 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=3.585e+07
2023-07-07 14:55:33,700 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:55:40,407 -        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 14:55:47,101 -        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 14:55:53,811 -        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 14:56:00,528 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 14:56:07,279 -        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 14:56:14,000 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 14:56:20,710 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=4.404e+07
2023-07-07 14:56:27,399 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.01, steps=4.507e+07
2023-07-07 14:56:34,103 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.01, steps=4.609e+07
2023-07-07 14:56:40,811 -        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 14:56:47,522 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=4.814e+07
2023-07-07 14:56:54,231 -        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 14:57:00,949 -        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 14:57:07,668 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=5.121e+07
2023-07-07 14:57:14,381 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.01, steps=5.223e+07
2023-07-07 14:57:21,075 -        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 14:57:27,786 -        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 14:57:34,474 -        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 14:57:41,190 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5500, best=0.62, avg=0.61, std=0.00, steps=5.633e+07
2023-07-07 14:57:47,913 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5600, best=0.66, avg=0.66, std=0.00, steps=5.735e+07
2023-07-07 14:57:54,630 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5700, best=0.69, avg=0.68, std=0.00, steps=5.838e+07
2023-07-07 14:58:01,360 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5800, best=0.70, avg=0.69, std=0.00, steps=5.940e+07
2023-07-07 14:58:08,086 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5900, best=0.71, avg=0.70, std=0.00, steps=6.043e+07
2023-07-07 14:58:14,827 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6000, best=0.72, avg=0.71, std=0.00, steps=6.145e+07
2023-07-07 14:58:21,541 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6100, best=0.72, avg=0.71, std=0.00, steps=6.247e+07
2023-07-07 14:58:28,247 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6200, best=0.73, avg=0.72, std=0.00, steps=6.350e+07
2023-07-07 14:58:34,971 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6300, best=0.74, avg=0.73, std=0.00, steps=6.452e+07
2023-07-07 14:58:41,709 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6400, best=0.74, avg=0.73, std=0.00, steps=6.555e+07
2023-07-07 14:58:48,430 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6500, best=0.75, avg=0.74, std=0.00, steps=6.657e+07
2023-07-07 14:58:55,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6600, best=0.75, avg=0.74, std=0.00, steps=6.759e+07
2023-07-07 14:59:01,875 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6700, best=0.76, avg=0.75, std=0.00, steps=6.862e+07
2023-07-07 14:59:08,589 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6800, best=0.76, avg=0.75, std=0.00, steps=6.964e+07
2023-07-07 14:59:15,292 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6900, best=0.76, avg=0.75, std=0.00, steps=7.067e+07
2023-07-07 14:59:22,011 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7000, best=0.77, avg=0.76, std=0.00, steps=7.169e+07
2023-07-07 14:59:28,718 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7100, best=0.77, avg=0.76, std=0.00, steps=7.271e+07
2023-07-07 14:59:35,437 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7200, best=0.77, avg=0.76, std=0.00, steps=7.374e+07
2023-07-07 14:59:42,150 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7300, best=0.77, avg=0.76, std=0.00, steps=7.476e+07
2023-07-07 14:59:48,878 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7400, best=0.78, avg=0.77, std=0.00, steps=7.579e+07
2023-07-07 14:59:55,629 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7500, best=0.78, avg=0.77, std=0.00, steps=7.681e+07
2023-07-07 15:00:02,362 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7600, best=0.78, avg=0.77, std=0.00, steps=7.783e+07
2023-07-07 15:00:09,093 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7700, best=0.79, avg=0.78, std=0.00, steps=7.886e+07
2023-07-07 15:00:15,815 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7800, best=0.79, avg=0.78, std=0.00, steps=7.988e+07
2023-07-07 15:00:22,537 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7900, best=0.79, avg=0.78, std=0.00, steps=8.091e+07
2023-07-07 15:00:29,246 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8000, best=0.80, avg=0.78, std=0.00, steps=8.193e+07
2023-07-07 15:00:35,949 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8100, best=0.80, avg=0.79, std=0.00, steps=8.295e+07
2023-07-07 15:00:42,642 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8200, best=0.80, avg=0.79, std=0.00, steps=8.398e+07
2023-07-07 15:00:49,353 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8300, best=0.80, avg=0.79, std=0.00, steps=8.500e+07
2023-07-07 15:00:56,051 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8400, best=0.80, avg=0.79, std=0.00, steps=8.603e+07
2023-07-07 15:01:02,771 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8500, best=0.81, avg=0.80, std=0.00, steps=8.705e+07
2023-07-07 15:01:09,474 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8600, best=0.81, avg=0.80, std=0.00, steps=8.807e+07
2023-07-07 15:01:16,183 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8700, best=0.81, avg=0.80, std=0.00, steps=8.910e+07
2023-07-07 15:01:22,919 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8800, best=0.81, avg=0.80, std=0.00, steps=9.012e+07
2023-07-07 15:01:29,632 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8900, best=0.81, avg=0.80, std=0.00, steps=9.115e+07
2023-07-07 15:01:36,329 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9000, best=0.81, avg=0.80, std=0.00, steps=9.217e+07
2023-07-07 15:01:43,024 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9100, best=0.81, avg=0.80, std=0.00, steps=9.319e+07
2023-07-07 15:01:49,735 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9200, best=0.81, avg=0.80, std=0.00, steps=9.422e+07
2023-07-07 15:01:56,449 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9300, best=0.81, avg=0.81, std=0.00, steps=9.524e+07
2023-07-07 15:02:03,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9400, best=0.81, avg=0.81, std=0.00, steps=9.627e+07
2023-07-07 15:02:09,871 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9500, best=0.82, avg=0.81, std=0.00, steps=9.729e+07
2023-07-07 15:02:16,582 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9600, best=0.82, avg=0.81, std=0.00, steps=9.831e+07
2023-07-07 15:02:23,304 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9700, best=0.82, avg=0.81, std=0.00, steps=9.934e+07
2023-07-07 15:02:30,028 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9800, best=0.82, avg=0.81, std=0.00, steps=1.004e+08
2023-07-07 15:02:36,725 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9900, best=0.82, avg=0.81, std=0.00, steps=1.014e+08
2023-07-07 15:02:43,459 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10000, best=0.82, avg=0.81, std=0.00, steps=1.024e+08
2023-07-07 15:02:50,184 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10100, best=0.82, avg=0.81, std=0.00, steps=1.034e+08
2023-07-07 15:02:56,905 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10200, best=0.82, avg=0.81, std=0.00, steps=1.045e+08
2023-07-07 15:03:03,626 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10300, best=0.83, avg=0.82, std=0.00, steps=1.055e+08
2023-07-07 15:03:10,327 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10400, best=0.82, avg=0.82, std=0.00, steps=1.065e+08
2023-07-07 15:03:17,027 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10500, best=0.83, avg=0.82, std=0.00, steps=1.075e+08
2023-07-07 15:03:23,741 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10600, best=0.83, avg=0.82, std=0.00, steps=1.086e+08
2023-07-07 15:03:30,458 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10700, best=0.83, avg=0.82, std=0.00, steps=1.096e+08
2023-07-07 15:03:37,172 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10800, best=0.83, avg=0.82, std=0.00, steps=1.106e+08
2023-07-07 15:03:43,880 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10900, best=0.83, avg=0.82, std=0.00, steps=1.116e+08
2023-07-07 15:03:50,592 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11000, best=0.83, avg=0.82, std=0.00, steps=1.127e+08
2023-07-07 15:03:57,317 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11100, best=0.83, avg=0.82, std=0.00, steps=1.137e+08
2023-07-07 15:04:04,026 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11200, best=0.83, avg=0.82, std=0.00, steps=1.147e+08
2023-07-07 15:04:10,734 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11300, best=0.83, avg=0.82, std=0.00, steps=1.157e+08
2023-07-07 15:04:17,423 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11400, best=0.83, avg=0.82, std=0.00, steps=1.167e+08
2023-07-07 15:04:24,125 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11500, best=0.83, avg=0.82, std=0.00, steps=1.178e+08
2023-07-07 15:04:30,828 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11600, best=0.83, avg=0.82, std=0.00, steps=1.188e+08
2023-07-07 15:04:37,538 -        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 15:04:44,251 -        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 15:04:50,963 -        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 15:04:57,605 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11999, best=0.84, avg=0.83, std=0.00, steps=1.229e+08
2023-07-07 15:04:57,606 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 15:04:57,630 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:04:57,630 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:04:57,661 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:05:07,230 -        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 15:05:15,200 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=2.470e+06
2023-07-07 15:05:23,176 -        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 15:05:31,168 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 15:05:39,176 -        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 15:05:47,149 -        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 15:05:55,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 15:06:03,111 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=9.843e+06
2023-07-07 15:06:11,102 -        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 15:06:19,124 -        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 15:06:27,122 -        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 15:06:35,117 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 15:06:43,097 -        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 15:06:51,059 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 15:06:59,056 -        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 15:07:07,061 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 15:07:15,066 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 15:07:23,056 -        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 15:07:31,064 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 15:07:39,077 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 15:07:47,060 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 15:07:55,050 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.01, steps=2.705e+07
2023-07-07 15:08:03,035 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 15:08:11,047 -        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 15:08:19,045 -        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 15:08:27,067 -        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 15:08:35,063 -        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 15:08:43,063 -        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 15:08:51,055 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 15:08:59,031 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 15:09:07,028 -        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 15:09:15,023 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=3.933e+07
2023-07-07 15:09:23,004 -        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 15:09:30,989 -        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 15:09:38,972 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 15:09:46,973 -        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 15:09:54,945 -        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 15:10:02,938 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 15:10:10,952 -        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 15:10:18,930 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 15:10:26,909 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 15:10:34,908 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 15:10:42,900 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 15:10:50,885 -        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 15:10:58,869 -        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 15:11:06,872 -        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 15:11:14,871 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=5.777e+07
2023-07-07 15:11:22,875 -        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 15:11:30,870 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 15:11:38,865 -        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 15:11:46,881 -        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 15:11:54,860 -        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 15:12:02,847 -        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 15:12:10,832 -        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 15:12:18,839 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 15:12:26,822 -        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 15:12:34,825 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=7.005e+07
2023-07-07 15:12:42,844 -        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 15:12:50,803 -        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 15:12:58,772 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 15:13:06,756 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 15:13:14,735 -        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 15:13:22,709 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 15:13:30,684 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6400, best=0.61, avg=0.60, std=0.00, steps=7.866e+07
2023-07-07 15:13:38,671 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6500, best=0.63, avg=0.62, std=0.00, steps=7.988e+07
2023-07-07 15:13:46,646 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6600, best=0.65, avg=0.64, std=0.00, steps=8.111e+07
2023-07-07 15:13:54,643 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6700, best=0.66, avg=0.65, std=0.00, steps=8.234e+07
2023-07-07 15:14:02,629 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6800, best=0.67, avg=0.66, std=0.00, steps=8.357e+07
2023-07-07 15:14:10,621 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6900, best=0.68, avg=0.67, std=0.00, steps=8.480e+07
2023-07-07 15:14:18,622 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7000, best=0.68, avg=0.67, std=0.00, steps=8.603e+07
2023-07-07 15:14:26,613 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7100, best=0.69, avg=0.68, std=0.00, steps=8.726e+07
2023-07-07 15:14:34,612 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7200, best=0.69, avg=0.68, std=0.00, steps=8.849e+07
2023-07-07 15:14:42,570 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7300, best=0.70, avg=0.69, std=0.00, steps=8.971e+07
2023-07-07 15:14:50,545 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7400, best=0.70, avg=0.69, std=0.00, steps=9.094e+07
2023-07-07 15:14:58,516 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7500, best=0.71, avg=0.70, std=0.00, steps=9.217e+07
2023-07-07 15:15:06,470 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7600, best=0.71, avg=0.70, std=0.00, steps=9.340e+07
2023-07-07 15:15:14,434 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7700, best=0.71, avg=0.70, std=0.00, steps=9.463e+07
2023-07-07 15:15:22,402 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7800, best=0.72, avg=0.71, std=0.00, steps=9.586e+07
2023-07-07 15:15:30,406 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7900, best=0.72, avg=0.71, std=0.00, steps=9.709e+07
2023-07-07 15:15:38,390 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8000, best=0.73, avg=0.71, std=0.00, steps=9.832e+07
2023-07-07 15:15:46,371 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8100, best=0.72, avg=0.72, std=0.00, steps=9.955e+07
2023-07-07 15:15:54,366 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8200, best=0.72, avg=0.72, std=0.00, steps=1.008e+08
2023-07-07 15:16:02,369 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8300, best=0.73, avg=0.72, std=0.00, steps=1.020e+08
2023-07-07 15:16:10,351 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8400, best=0.73, avg=0.72, std=0.00, steps=1.032e+08
2023-07-07 15:16:18,321 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8500, best=0.73, avg=0.72, std=0.00, steps=1.045e+08
2023-07-07 15:16:26,299 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8600, best=0.74, avg=0.72, std=0.00, steps=1.057e+08
2023-07-07 15:16:34,278 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8700, best=0.74, avg=0.73, std=0.00, steps=1.069e+08
2023-07-07 15:16:42,256 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8800, best=0.74, avg=0.73, std=0.00, steps=1.081e+08
2023-07-07 15:16:50,248 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8900, best=0.74, avg=0.73, std=0.00, steps=1.094e+08
2023-07-07 15:16:58,240 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9000, best=0.75, avg=0.73, std=0.00, steps=1.106e+08
2023-07-07 15:17:06,230 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9100, best=0.75, avg=0.74, std=0.00, steps=1.118e+08
2023-07-07 15:17:14,211 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9200, best=0.75, avg=0.74, std=0.00, steps=1.131e+08
2023-07-07 15:17:22,211 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9300, best=0.75, avg=0.74, std=0.00, steps=1.143e+08
2023-07-07 15:17:30,205 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9400, best=0.75, avg=0.74, std=0.00, steps=1.155e+08
2023-07-07 15:17:38,191 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9500, best=0.76, avg=0.75, std=0.00, steps=1.167e+08
2023-07-07 15:17:46,173 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9600, best=0.76, avg=0.75, std=0.00, steps=1.180e+08
2023-07-07 15:17:54,160 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9700, best=0.76, avg=0.75, std=0.00, steps=1.192e+08
2023-07-07 15:18:02,123 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9800, best=0.76, avg=0.75, std=0.00, steps=1.204e+08
2023-07-07 15:18:10,095 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9900, best=0.76, avg=0.75, std=0.00, steps=1.217e+08
2023-07-07 15:18:18,084 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10000, best=0.77, avg=0.76, std=0.00, steps=1.229e+08
2023-07-07 15:18:26,070 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10100, best=0.77, avg=0.76, std=0.00, steps=1.241e+08
2023-07-07 15:18:34,053 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10200, best=0.77, avg=0.76, std=0.00, steps=1.253e+08
2023-07-07 15:18:42,020 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10300, best=0.77, avg=0.76, std=0.00, steps=1.266e+08
2023-07-07 15:18:50,005 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10400, best=0.78, avg=0.76, std=0.00, steps=1.278e+08
2023-07-07 15:18:58,013 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10500, best=0.77, avg=0.76, std=0.00, steps=1.290e+08
2023-07-07 15:19:06,008 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10600, best=0.78, avg=0.77, std=0.00, steps=1.303e+08
2023-07-07 15:19:13,996 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10700, best=0.78, avg=0.77, std=0.00, steps=1.315e+08
2023-07-07 15:19:21,984 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10800, best=0.78, avg=0.77, std=0.00, steps=1.327e+08
2023-07-07 15:19:29,968 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10900, best=0.78, avg=0.77, std=0.00, steps=1.340e+08
2023-07-07 15:19:37,960 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11000, best=0.79, avg=0.78, std=0.00, steps=1.352e+08
2023-07-07 15:19:45,944 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11100, best=0.79, avg=0.78, std=0.00, steps=1.364e+08
2023-07-07 15:19:53,902 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11200, best=0.79, avg=0.78, std=0.00, steps=1.376e+08
2023-07-07 15:20:01,883 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11300, best=0.79, avg=0.78, std=0.00, steps=1.389e+08
2023-07-07 15:20:09,874 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11400, best=0.79, avg=0.78, std=0.00, steps=1.401e+08
2023-07-07 15:20:17,870 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11500, best=0.79, avg=0.79, std=0.00, steps=1.413e+08
2023-07-07 15:20:25,846 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11600, best=0.80, avg=0.79, std=0.00, steps=1.426e+08
2023-07-07 15:20:33,820 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11700, best=0.80, avg=0.79, std=0.00, steps=1.438e+08
2023-07-07 15:20:41,802 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11800, best=0.80, avg=0.79, std=0.00, steps=1.450e+08
2023-07-07 15:20:49,766 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11900, best=0.80, avg=0.79, std=0.00, steps=1.462e+08
2023-07-07 15:20:57,676 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11999, best=0.80, avg=0.79, std=0.00, steps=1.475e+08
2023-07-07 15:20:57,677 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 15:20:57,705 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:20:57,706 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:20:57,739 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:21:09,947 -        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 15:21:20,530 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=3.293e+06
2023-07-07 15:21:31,108 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 300, best=0.51, avg=0.50, std=0.01, steps=4.932e+06
2023-07-07 15:21:41,695 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=6.570e+06
2023-07-07 15:21:52,303 -        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 15:22:02,891 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=9.847e+06
2023-07-07 15:22:13,483 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=1.149e+07
2023-07-07 15:22:24,102 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 15:22:34,675 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 900, best=0.51, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 15:22:45,265 -        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 15:22:55,857 -        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 15:23:06,440 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.01, steps=1.968e+07
2023-07-07 15:23:17,016 -        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 15:23:27,597 -        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 15:23:38,162 -        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 15:23:48,737 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=2.623e+07
2023-07-07 15:23:59,335 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.787e+07
2023-07-07 15:24:09,917 -        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 15:24:20,504 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.01, steps=3.115e+07
2023-07-07 15:24:31,096 -        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 15:24:41,661 -        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 15:24:52,246 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.01, steps=3.606e+07
2023-07-07 15:25:02,808 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.01, steps=3.770e+07
2023-07-07 15:25:13,391 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.01, steps=3.934e+07
2023-07-07 15:25:23,959 -        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 15:25:34,539 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 15:25:45,125 -        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 15:25:55,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.01, steps=4.589e+07
2023-07-07 15:26:06,268 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=4.753e+07
2023-07-07 15:26:16,841 -        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 15:26:27,418 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=5.081e+07
2023-07-07 15:26:37,996 -        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 15:26:48,575 -        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 15:26:59,152 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=5.572e+07
2023-07-07 15:27:09,720 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=5.736e+07
2023-07-07 15:27:20,295 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.01, steps=5.900e+07
2023-07-07 15:27:30,875 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=6.064e+07
2023-07-07 15:27:41,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=6.228e+07
2023-07-07 15:27:52,027 -        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 15:28:02,620 -        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 15:28:13,205 -        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 15:28:23,780 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 15:28:34,358 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=7.047e+07
2023-07-07 15:28:44,941 -        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 15:28:55,510 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 15:29:06,076 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=7.538e+07
2023-07-07 15:29:16,668 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=7.702e+07
2023-07-07 15:29:27,251 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 15:29:37,817 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.01, steps=8.030e+07
2023-07-07 15:29:48,396 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=8.194e+07
2023-07-07 15:29:58,966 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 15:30:09,543 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=8.521e+07
2023-07-07 15:30:20,168 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=8.685e+07
2023-07-07 15:30:30,736 -        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 15:30:41,326 -        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 15:30:51,928 -        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 15:31:02,514 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=9.341e+07
2023-07-07 15:31:13,113 -        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 15:31:23,704 -        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 15:31:34,275 -        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 15:31:44,850 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.01, steps=9.996e+07
2023-07-07 15:31:55,424 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=1.016e+08
2023-07-07 15:32:06,008 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 15:32:16,587 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.01, steps=1.049e+08
2023-07-07 15:32:27,171 -        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 15:32:37,742 -        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 15:32:48,320 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.01, steps=1.098e+08
2023-07-07 15:32:58,896 -        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 15:33:09,486 -        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 15:33:20,085 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 15:33:30,688 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.01, steps=1.163e+08
2023-07-07 15:33:41,282 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 15:33:51,844 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.196e+08
2023-07-07 15:34:02,392 -        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 15:34:12,961 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 15:34:23,542 -        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 15:34:34,127 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.01, steps=1.262e+08
2023-07-07 15:34:44,721 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.278e+08
2023-07-07 15:34:55,290 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.294e+08
2023-07-07 15:35:05,875 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 15:35:16,460 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.01, steps=1.327e+08
2023-07-07 15:35:27,022 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.344e+08
2023-07-07 15:35:37,593 -        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 15:35:48,179 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.01, steps=1.376e+08
2023-07-07 15:35:58,772 -        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 15:36:09,337 -        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 15:36:19,920 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.426e+08
2023-07-07 15:36:30,490 -        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 15:36:41,051 -        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 15:36:51,665 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.01, steps=1.475e+08
2023-07-07 15:37:02,239 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.00, steps=1.491e+08
2023-07-07 15:37:12,802 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.01, steps=1.507e+08
2023-07-07 15:37:23,364 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.01, steps=1.524e+08
2023-07-07 15:37:33,918 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.01, steps=1.540e+08
2023-07-07 15:37:44,474 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=1.557e+08
2023-07-07 15:37:55,043 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.573e+08
2023-07-07 15:38:05,625 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.01, steps=1.589e+08
2023-07-07 15:38:16,192 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.00, steps=1.606e+08
2023-07-07 15:38:26,743 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.01, steps=1.622e+08
2023-07-07 15:38:37,302 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=1.639e+08
2023-07-07 15:38:47,882 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=1.655e+08
2023-07-07 15:38:58,446 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.01, steps=1.671e+08
2023-07-07 15:39:09,019 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=1.688e+08
2023-07-07 15:39:19,609 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.01, steps=1.704e+08
2023-07-07 15:39:30,204 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.01, steps=1.720e+08
2023-07-07 15:39:40,793 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.01, steps=1.737e+08
2023-07-07 15:39:51,379 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.01, steps=1.753e+08
2023-07-07 15:40:01,992 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.01, steps=1.770e+08
2023-07-07 15:40:12,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10900, best=0.52, avg=0.50, std=0.01, steps=1.786e+08
2023-07-07 15:40:23,154 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.01, steps=1.802e+08
2023-07-07 15:40:33,740 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.01, steps=1.819e+08
2023-07-07 15:40:44,356 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=1.835e+08
2023-07-07 15:40:54,954 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11300, best=0.52, avg=0.50, std=0.01, steps=1.852e+08
2023-07-07 15:41:05,542 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.01, steps=1.868e+08
2023-07-07 15:41:16,148 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11500, best=0.52, avg=0.50, std=0.01, steps=1.884e+08
2023-07-07 15:41:26,744 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11600, best=0.52, avg=0.50, std=0.01, steps=1.901e+08
2023-07-07 15:41:37,370 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.01, steps=1.917e+08
2023-07-07 15:41:47,962 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.01, steps=1.933e+08
2023-07-07 15:41:58,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.01, steps=1.950e+08
2023-07-07 15:42:09,064 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.01, steps=1.966e+08
2023-07-07 15:42:09,066 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 15:42:09,091 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:42:09,091 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:42:09,123 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:42:21,566 -        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 15:42:32,132 -        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 15:42:42,720 -        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 15:42:53,316 -        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 15:43:03,911 -        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 15:43:14,475 -        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 15:43:25,020 -        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 15:43:35,575 -        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 15:43:46,112 -        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 15:43:56,655 -        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 15:44:07,216 -        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 15:44:17,788 -        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 15:44:28,329 -        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 15:44:38,912 -        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 15:44:49,480 -        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 15:45:00,038 -        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 15:45:10,593 -        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 15:45:21,162 -        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 15:45:31,722 -        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 15:45:42,269 -        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 15:45:52,809 -        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 15:46:03,363 -        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 15:46:13,955 -        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 15:46:24,538 -        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 15:46:35,077 -        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 15:46:45,619 -        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 15:46:56,198 -        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 15:47:06,754 -        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 15:47:17,286 -        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 15:47:27,826 -        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 15:47:38,358 -        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 15:47:48,898 -        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 15:47:59,440 -        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 15:48:09,970 -        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 15:48:20,494 -        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 15:48:31,030 -        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 15:48:41,582 -        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 15:48:52,131 -        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 15:49:02,668 -        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 15:49:13,203 -        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 15:49:23,729 -        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 15:49:34,305 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=6.883e+07
2023-07-07 15:49:44,863 -        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 15:49:55,405 -        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 15:50:05,935 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4500, best=0.58, avg=0.57, std=0.00, steps=7.374e+07
2023-07-07 15:50:16,493 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4600, best=0.62, avg=0.61, std=0.00, steps=7.538e+07
2023-07-07 15:50:27,037 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4700, best=0.64, avg=0.63, std=0.00, steps=7.702e+07
2023-07-07 15:50:37,588 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4800, best=0.66, avg=0.65, std=0.00, steps=7.866e+07
2023-07-07 15:50:48,134 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4900, best=0.66, avg=0.66, std=0.00, steps=8.030e+07
2023-07-07 15:50:58,674 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5000, best=0.67, avg=0.66, std=0.00, steps=8.194e+07
2023-07-07 15:51:09,223 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5100, best=0.68, avg=0.67, std=0.00, steps=8.357e+07
2023-07-07 15:51:19,778 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5200, best=0.68, avg=0.67, std=0.00, steps=8.521e+07
2023-07-07 15:51:30,328 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5300, best=0.69, avg=0.68, std=0.00, steps=8.685e+07
2023-07-07 15:51:40,871 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5400, best=0.69, avg=0.69, std=0.00, steps=8.849e+07
2023-07-07 15:51:51,415 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5500, best=0.70, avg=0.69, std=0.00, steps=9.013e+07
2023-07-07 15:52:01,957 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5600, best=0.70, avg=0.69, std=0.00, steps=9.177e+07
2023-07-07 15:52:12,506 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5700, best=0.70, avg=0.70, std=0.00, steps=9.341e+07
2023-07-07 15:52:23,061 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5800, best=0.71, avg=0.70, std=0.00, steps=9.504e+07
2023-07-07 15:52:33,613 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5900, best=0.71, avg=0.70, std=0.00, steps=9.668e+07
2023-07-07 15:52:44,163 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6000, best=0.71, avg=0.70, std=0.00, steps=9.832e+07
2023-07-07 15:52:54,723 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6100, best=0.71, avg=0.71, std=0.00, steps=9.996e+07
2023-07-07 15:53:05,268 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6200, best=0.72, avg=0.71, std=0.00, steps=1.016e+08
2023-07-07 15:53:15,809 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6300, best=0.72, avg=0.71, std=0.00, steps=1.032e+08
2023-07-07 15:53:26,367 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6400, best=0.72, avg=0.71, std=0.00, steps=1.049e+08
2023-07-07 15:53:36,921 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6500, best=0.72, avg=0.71, std=0.00, steps=1.065e+08
2023-07-07 15:53:47,475 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6600, best=0.72, avg=0.72, std=0.00, steps=1.082e+08
2023-07-07 15:53:58,028 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6700, best=0.72, avg=0.72, std=0.00, steps=1.098e+08
2023-07-07 15:54:08,569 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6800, best=0.73, avg=0.72, std=0.00, steps=1.114e+08
2023-07-07 15:54:19,117 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6900, best=0.73, avg=0.72, std=0.00, steps=1.131e+08
2023-07-07 15:54:29,660 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7000, best=0.73, avg=0.72, std=0.00, steps=1.147e+08
2023-07-07 15:54:40,194 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7100, best=0.73, avg=0.72, std=0.00, steps=1.163e+08
2023-07-07 15:54:50,753 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7200, best=0.73, avg=0.73, std=0.00, steps=1.180e+08
2023-07-07 15:55:01,295 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7300, best=0.73, avg=0.73, std=0.00, steps=1.196e+08
2023-07-07 15:55:11,823 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7400, best=0.74, avg=0.73, std=0.00, steps=1.213e+08
2023-07-07 15:55:22,368 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7500, best=0.74, avg=0.73, std=0.00, steps=1.229e+08
2023-07-07 15:55:32,903 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7600, best=0.74, avg=0.73, std=0.00, steps=1.245e+08
2023-07-07 15:55:43,450 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7700, best=0.74, avg=0.73, std=0.00, steps=1.262e+08
2023-07-07 15:55:53,986 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7800, best=0.74, avg=0.73, std=0.00, steps=1.278e+08
2023-07-07 15:56:04,527 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7900, best=0.74, avg=0.73, std=0.00, steps=1.294e+08
2023-07-07 15:56:15,070 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8000, best=0.74, avg=0.74, std=0.00, steps=1.311e+08
2023-07-07 15:56:25,598 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8100, best=0.74, avg=0.74, std=0.00, steps=1.327e+08
2023-07-07 15:56:36,149 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8200, best=0.74, avg=0.74, std=0.00, steps=1.344e+08
2023-07-07 15:56:46,686 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8300, best=0.75, avg=0.74, std=0.00, steps=1.360e+08
2023-07-07 15:56:57,234 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8400, best=0.75, avg=0.74, std=0.00, steps=1.376e+08
2023-07-07 15:57:07,761 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8500, best=0.75, avg=0.74, std=0.00, steps=1.393e+08
2023-07-07 15:57:18,300 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8600, best=0.75, avg=0.74, std=0.00, steps=1.409e+08
2023-07-07 15:57:28,831 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8700, best=0.75, avg=0.74, std=0.00, steps=1.426e+08
2023-07-07 15:57:39,371 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8800, best=0.75, avg=0.74, std=0.00, steps=1.442e+08
2023-07-07 15:57:49,926 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8900, best=0.75, avg=0.75, std=0.00, steps=1.458e+08
2023-07-07 15:58:00,484 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9000, best=0.75, avg=0.75, std=0.00, steps=1.475e+08
2023-07-07 15:58:11,036 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9100, best=0.76, avg=0.75, std=0.00, steps=1.491e+08
2023-07-07 15:58:21,581 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9200, best=0.76, avg=0.75, std=0.00, steps=1.507e+08
2023-07-07 15:58:32,133 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9300, best=0.76, avg=0.75, std=0.00, steps=1.524e+08
2023-07-07 15:58:42,684 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9400, best=0.76, avg=0.75, std=0.00, steps=1.540e+08
2023-07-07 15:58:53,217 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9500, best=0.76, avg=0.75, std=0.00, steps=1.557e+08
2023-07-07 15:59:03,753 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9600, best=0.76, avg=0.75, std=0.00, steps=1.573e+08
2023-07-07 15:59:14,291 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9700, best=0.77, avg=0.76, std=0.00, steps=1.589e+08
2023-07-07 15:59:24,823 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9800, best=0.77, avg=0.76, std=0.00, steps=1.606e+08
2023-07-07 15:59:35,358 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9900, best=0.76, avg=0.76, std=0.00, steps=1.622e+08
2023-07-07 15:59:45,903 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10000, best=0.77, avg=0.76, std=0.00, steps=1.639e+08
2023-07-07 15:59:56,444 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10100, best=0.77, avg=0.76, std=0.00, steps=1.655e+08
2023-07-07 16:00:06,966 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10200, best=0.77, avg=0.76, std=0.00, steps=1.671e+08
2023-07-07 16:00:17,494 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10300, best=0.77, avg=0.76, std=0.00, steps=1.688e+08
2023-07-07 16:00:28,031 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10400, best=0.77, avg=0.76, std=0.00, steps=1.704e+08
2023-07-07 16:00:38,573 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10500, best=0.77, avg=0.77, std=0.00, steps=1.720e+08
2023-07-07 16:00:49,120 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10600, best=0.77, avg=0.77, std=0.00, steps=1.737e+08
2023-07-07 16:00:59,656 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10700, best=0.78, avg=0.77, std=0.00, steps=1.753e+08
2023-07-07 16:01:10,184 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10800, best=0.78, avg=0.77, std=0.00, steps=1.770e+08
2023-07-07 16:01:20,703 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10900, best=0.78, avg=0.77, std=0.00, steps=1.786e+08
2023-07-07 16:01:31,225 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11000, best=0.78, avg=0.77, std=0.00, steps=1.802e+08
2023-07-07 16:01:41,751 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11100, best=0.78, avg=0.77, std=0.00, steps=1.819e+08
2023-07-07 16:01:52,288 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11200, best=0.78, avg=0.77, std=0.00, steps=1.835e+08
2023-07-07 16:02:02,819 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11300, best=0.78, avg=0.78, std=0.00, steps=1.852e+08
2023-07-07 16:02:13,355 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11400, best=0.78, avg=0.78, std=0.00, steps=1.868e+08
2023-07-07 16:02:23,883 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11500, best=0.78, avg=0.78, std=0.00, steps=1.884e+08
2023-07-07 16:02:34,435 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11600, best=0.78, avg=0.78, std=0.00, steps=1.901e+08
2023-07-07 16:02:44,975 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11700, best=0.79, avg=0.78, std=0.00, steps=1.917e+08
2023-07-07 16:02:55,521 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11800, best=0.78, avg=0.78, std=0.00, steps=1.933e+08
2023-07-07 16:03:06,057 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11900, best=0.79, avg=0.78, std=0.00, steps=1.950e+08
2023-07-07 16:03:16,479 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11999, best=0.79, avg=0.78, std=0.00, steps=1.966e+08
2023-07-07 16:03:16,479 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 16:03:16,504 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:03:16,504 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:03:16,540 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:03:30,045 -        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 16:03:41,916 -        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 16:03:53,785 -        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 16:04:05,651 -        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 16:04:17,507 -        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 16:04:29,387 -        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 16:04:41,250 -        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 16:04:53,105 -        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 16:05:04,980 -        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 16:05:16,862 -        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 16:05:28,764 -        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 16:05:40,634 -        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 16:05:52,496 -        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 16:06:04,387 -        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 16:06:16,261 -        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 16:06:28,109 -        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 16:06:39,952 -        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 16:06:51,799 -        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 16:07:03,653 -        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 16:07:15,524 -        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 16:07:27,382 -        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 16:07:39,267 -        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 16:07:51,125 -        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 16:08:02,985 -        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 16:08:14,832 -        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 16:08:26,688 -        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 16:08:38,531 -        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 16:08:50,392 -        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 16:09:02,251 -        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 16:09:14,114 -        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 16:09:25,979 -        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 16:09:37,841 -        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 16:09:49,694 -        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 16:10:01,536 -        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 16:10:13,376 -        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 16:10:25,227 -        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 16:10:37,074 -        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 16:10:48,932 -        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 16:11:00,778 -        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 16:11:12,622 -        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 16:11:24,468 -        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 16:11:36,320 -        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 16:11:48,182 -        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 16:12:00,057 -        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 16:12:11,972 -        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 16:12:23,842 -        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 16:12:35,696 -        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 16:12:47,567 -        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 16:12:59,429 -        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 16:13:11,289 -        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 16:13:23,149 -        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 16:13:35,001 -        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 16:13:46,850 -        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 16:13:58,701 -        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 16:14:10,544 -        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 16:14:22,385 -        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 16:14:34,227 -        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 16:14:46,075 -        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 16:14:57,927 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5900, best=0.57, avg=0.57, std=0.00, steps=1.088e+08
2023-07-07 16:15:09,785 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6000, best=0.60, avg=0.59, std=0.00, steps=1.106e+08
2023-07-07 16:15:21,639 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6100, best=0.61, avg=0.61, std=0.00, steps=1.125e+08
2023-07-07 16:15:33,500 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6200, best=0.62, avg=0.61, std=0.00, steps=1.143e+08
2023-07-07 16:15:45,368 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6300, best=0.63, avg=0.62, std=0.00, steps=1.161e+08
2023-07-07 16:15:57,220 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6400, best=0.64, avg=0.63, std=0.00, steps=1.180e+08
2023-07-07 16:16:09,075 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6500, best=0.65, avg=0.64, std=0.00, steps=1.198e+08
2023-07-07 16:16:20,924 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6600, best=0.65, avg=0.64, std=0.00, steps=1.217e+08
2023-07-07 16:16:32,780 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6700, best=0.66, avg=0.65, std=0.00, steps=1.235e+08
2023-07-07 16:16:44,637 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6800, best=0.66, avg=0.66, std=0.00, steps=1.254e+08
2023-07-07 16:16:56,507 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6900, best=0.67, avg=0.66, std=0.00, steps=1.272e+08
2023-07-07 16:17:08,368 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7000, best=0.67, avg=0.66, std=0.00, steps=1.290e+08
2023-07-07 16:17:20,218 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7100, best=0.67, avg=0.66, std=0.00, steps=1.309e+08
2023-07-07 16:17:32,074 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7200, best=0.67, avg=0.67, std=0.00, steps=1.327e+08
2023-07-07 16:17:43,921 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7300, best=0.68, avg=0.67, std=0.00, steps=1.346e+08
2023-07-07 16:17:55,801 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7400, best=0.68, avg=0.67, std=0.00, steps=1.364e+08
2023-07-07 16:18:07,655 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7500, best=0.68, avg=0.67, std=0.00, steps=1.383e+08
2023-07-07 16:18:19,492 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7600, best=0.68, avg=0.68, std=0.00, steps=1.401e+08
2023-07-07 16:18:31,328 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7700, best=0.69, avg=0.68, std=0.00, steps=1.419e+08
2023-07-07 16:18:43,208 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7800, best=0.69, avg=0.68, std=0.00, steps=1.438e+08
2023-07-07 16:18:55,046 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7900, best=0.69, avg=0.68, std=0.00, steps=1.456e+08
2023-07-07 16:19:06,886 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8000, best=0.69, avg=0.68, std=0.00, steps=1.475e+08
2023-07-07 16:19:18,727 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8100, best=0.69, avg=0.68, std=0.00, steps=1.493e+08
2023-07-07 16:19:30,579 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8200, best=0.69, avg=0.68, std=0.00, steps=1.512e+08
2023-07-07 16:19:42,424 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8300, best=0.69, avg=0.69, std=0.00, steps=1.530e+08
2023-07-07 16:19:54,293 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8400, best=0.70, avg=0.69, std=0.00, steps=1.548e+08
2023-07-07 16:20:06,147 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8500, best=0.69, avg=0.69, std=0.00, steps=1.567e+08
2023-07-07 16:20:18,018 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8600, best=0.70, avg=0.69, std=0.00, steps=1.585e+08
2023-07-07 16:20:29,865 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8700, best=0.70, avg=0.69, std=0.00, steps=1.604e+08
2023-07-07 16:20:41,727 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8800, best=0.70, avg=0.69, std=0.00, steps=1.622e+08
2023-07-07 16:20:53,570 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8900, best=0.70, avg=0.69, std=0.00, steps=1.641e+08
2023-07-07 16:21:05,432 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9000, best=0.70, avg=0.69, std=0.00, steps=1.659e+08
2023-07-07 16:21:17,296 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9100, best=0.70, avg=0.69, std=0.00, steps=1.677e+08
2023-07-07 16:21:29,149 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9200, best=0.70, avg=0.70, std=0.00, steps=1.696e+08
2023-07-07 16:21:41,019 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9300, best=0.70, avg=0.70, std=0.00, steps=1.714e+08
2023-07-07 16:21:52,889 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9400, best=0.70, avg=0.70, std=0.00, steps=1.733e+08
2023-07-07 16:22:04,752 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9500, best=0.71, avg=0.70, std=0.00, steps=1.751e+08
2023-07-07 16:22:16,611 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9600, best=0.71, avg=0.70, std=0.00, steps=1.770e+08
2023-07-07 16:22:28,478 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9700, best=0.71, avg=0.70, std=0.00, steps=1.788e+08
2023-07-07 16:22:40,409 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9800, best=0.71, avg=0.70, std=0.00, steps=1.807e+08
2023-07-07 16:22:52,272 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9900, best=0.71, avg=0.70, std=0.00, steps=1.825e+08
2023-07-07 16:23:04,125 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10000, best=0.71, avg=0.70, std=0.00, steps=1.843e+08
2023-07-07 16:23:15,982 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10100, best=0.71, avg=0.70, std=0.00, steps=1.862e+08
2023-07-07 16:23:27,834 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10200, best=0.71, avg=0.70, std=0.00, steps=1.880e+08
2023-07-07 16:23:39,695 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10300, best=0.71, avg=0.70, std=0.00, steps=1.899e+08
2023-07-07 16:23:51,619 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10400, best=0.71, avg=0.71, std=0.00, steps=1.917e+08
2023-07-07 16:24:03,531 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10500, best=0.71, avg=0.71, std=0.00, steps=1.936e+08
2023-07-07 16:24:15,447 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10600, best=0.71, avg=0.71, std=0.00, steps=1.954e+08
2023-07-07 16:24:27,286 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10700, best=0.72, avg=0.71, std=0.00, steps=1.972e+08
2023-07-07 16:24:39,138 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10800, best=0.71, avg=0.71, std=0.00, steps=1.991e+08
2023-07-07 16:24:51,045 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10900, best=0.71, avg=0.71, std=0.00, steps=2.009e+08
2023-07-07 16:25:02,952 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11000, best=0.72, avg=0.71, std=0.00, steps=2.028e+08
2023-07-07 16:25:14,846 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11100, best=0.72, avg=0.71, std=0.00, steps=2.046e+08
2023-07-07 16:25:26,712 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11200, best=0.72, avg=0.71, std=0.00, steps=2.065e+08
2023-07-07 16:25:38,611 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11300, best=0.72, avg=0.71, std=0.00, steps=2.083e+08
2023-07-07 16:25:50,550 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11400, best=0.72, avg=0.71, std=0.00, steps=2.101e+08
2023-07-07 16:26:02,433 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11500, best=0.72, avg=0.71, std=0.00, steps=2.120e+08
2023-07-07 16:26:14,307 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11600, best=0.72, avg=0.71, std=0.00, steps=2.138e+08
2023-07-07 16:26:26,169 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11700, best=0.72, avg=0.72, std=0.00, steps=2.157e+08
2023-07-07 16:26:38,057 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11800, best=0.73, avg=0.72, std=0.00, steps=2.175e+08
2023-07-07 16:26:50,014 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11900, best=0.72, avg=0.72, std=0.00, steps=2.194e+08
2023-07-07 16:27:01,759 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11999, best=0.72, avg=0.72, std=0.00, steps=2.212e+08
2023-07-07 16:27:01,760 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 16:27:01,788 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:27:01,788 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:27:01,825 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:27:16,609 -        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 16:27:29,745 -        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 16:27:42,875 -        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 16:27:56,005 -        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 16:28:09,194 -        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 16:28:22,358 -        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 16:28:35,497 -        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 16:28:48,656 -        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 16:29:01,826 -        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 16:29:14,990 -        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 16:29:28,127 -        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 16:29:41,304 -        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 16:29:54,465 -        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 16:30:07,597 -        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 16:30:20,736 -        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 16:30:33,910 -        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 16:30:47,071 -        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 16:31:00,222 -        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 16:31:13,362 -        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 16:31:26,506 -        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 16:31:39,650 -        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 16:31:52,786 -        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 16:32:05,930 -        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 16:32:19,103 -        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 16:32:32,269 -        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 16:32:45,433 -        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 16:32:58,593 -        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 16:33:11,759 -        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 16:33:24,907 -        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 16:33:38,076 -        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 16:33:51,299 -        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 16:34:04,463 -        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 16:34:17,597 -        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 16:34:30,727 -        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 16:34:43,859 -        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 16:34:57,005 -        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 16:35:10,154 -        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 16:35:23,342 -        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 16:35:36,490 -        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 16:35:49,632 -        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 16:36:02,847 -        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 16:36:16,024 -        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 16:36:29,173 -        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 16:36:42,307 -        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 16:36:55,434 -        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 16:37:08,585 -        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 16:37:21,781 -        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 16:37:35,012 -        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 16:37:48,140 -        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 16:38:01,298 -        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 16:38:14,465 -        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 16:38:27,593 -        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 16:38:40,707 -        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 16:38:53,828 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5400, best=0.55, avg=0.55, std=0.00, steps=1.106e+08
2023-07-07 16:39:07,098 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5500, best=0.59, avg=0.58, std=0.00, steps=1.127e+08
2023-07-07 16:39:20,299 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5600, best=0.60, avg=0.59, std=0.00, steps=1.147e+08
2023-07-07 16:39:33,474 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5700, best=0.61, avg=0.60, std=0.00, steps=1.168e+08
2023-07-07 16:39:46,628 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5800, best=0.62, avg=0.61, std=0.00, steps=1.188e+08
2023-07-07 16:39:59,766 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5900, best=0.63, avg=0.62, std=0.00, steps=1.209e+08
2023-07-07 16:40:12,910 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6000, best=0.63, avg=0.63, std=0.00, steps=1.229e+08
2023-07-07 16:40:26,070 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6100, best=0.64, avg=0.63, std=0.00, steps=1.249e+08
2023-07-07 16:40:39,230 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6200, best=0.64, avg=0.64, std=0.00, steps=1.270e+08
2023-07-07 16:40:52,377 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6300, best=0.65, avg=0.64, std=0.00, steps=1.290e+08
2023-07-07 16:41:05,541 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6400, best=0.65, avg=0.64, std=0.00, steps=1.311e+08
2023-07-07 16:41:18,697 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6500, best=0.66, avg=0.65, std=0.00, steps=1.331e+08
2023-07-07 16:41:31,828 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6600, best=0.66, avg=0.65, std=0.00, steps=1.352e+08
2023-07-07 16:41:44,985 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6700, best=0.66, avg=0.65, std=0.00, steps=1.372e+08
2023-07-07 16:41:58,125 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6800, best=0.66, avg=0.65, std=0.00, steps=1.393e+08
2023-07-07 16:42:11,251 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6900, best=0.66, avg=0.65, std=0.00, steps=1.413e+08
2023-07-07 16:42:24,419 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7000, best=0.66, avg=0.66, std=0.00, steps=1.434e+08
2023-07-07 16:42:37,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7100, best=0.66, avg=0.66, std=0.00, steps=1.454e+08
2023-07-07 16:42:50,792 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7200, best=0.67, avg=0.66, std=0.00, steps=1.475e+08
2023-07-07 16:43:03,920 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7300, best=0.67, avg=0.66, std=0.00, steps=1.495e+08
2023-07-07 16:43:17,058 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7400, best=0.67, avg=0.66, std=0.00, steps=1.516e+08
2023-07-07 16:43:30,177 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7500, best=0.67, avg=0.66, std=0.00, steps=1.536e+08
2023-07-07 16:43:43,316 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7600, best=0.67, avg=0.67, std=0.00, steps=1.557e+08
2023-07-07 16:43:56,515 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7700, best=0.68, avg=0.67, std=0.00, steps=1.577e+08
2023-07-07 16:44:09,736 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7800, best=0.67, avg=0.67, std=0.00, steps=1.598e+08
2023-07-07 16:44:22,858 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7900, best=0.68, avg=0.67, std=0.00, steps=1.618e+08
2023-07-07 16:44:36,024 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8000, best=0.68, avg=0.67, std=0.00, steps=1.639e+08
2023-07-07 16:44:49,197 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8100, best=0.68, avg=0.67, std=0.00, steps=1.659e+08
2023-07-07 16:45:02,329 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8200, best=0.68, avg=0.67, std=0.00, steps=1.680e+08
2023-07-07 16:45:15,550 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8300, best=0.68, avg=0.68, std=0.00, steps=1.700e+08
2023-07-07 16:45:28,752 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8400, best=0.68, avg=0.68, std=0.00, steps=1.721e+08
2023-07-07 16:45:41,896 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8500, best=0.68, avg=0.68, std=0.00, steps=1.741e+08
2023-07-07 16:45:55,021 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8600, best=0.69, avg=0.68, std=0.00, steps=1.761e+08
2023-07-07 16:46:08,157 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8700, best=0.68, avg=0.68, std=0.00, steps=1.782e+08
2023-07-07 16:46:21,305 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8800, best=0.69, avg=0.68, std=0.00, steps=1.802e+08
2023-07-07 16:46:34,432 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8900, best=0.69, avg=0.68, std=0.00, steps=1.823e+08
2023-07-07 16:46:47,613 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9000, best=0.69, avg=0.68, std=0.00, steps=1.843e+08
2023-07-07 16:47:00,834 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9100, best=0.69, avg=0.68, std=0.00, steps=1.864e+08
2023-07-07 16:47:13,990 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9200, best=0.69, avg=0.68, std=0.00, steps=1.884e+08
2023-07-07 16:47:27,140 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9300, best=0.69, avg=0.69, std=0.00, steps=1.905e+08
2023-07-07 16:47:40,378 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9400, best=0.69, avg=0.69, std=0.00, steps=1.925e+08
2023-07-07 16:47:53,537 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9500, best=0.69, avg=0.69, std=0.00, steps=1.946e+08
2023-07-07 16:48:06,669 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9600, best=0.70, avg=0.69, std=0.00, steps=1.966e+08
2023-07-07 16:48:19,802 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9700, best=0.69, avg=0.69, std=0.00, steps=1.987e+08
2023-07-07 16:48:32,931 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9800, best=0.70, avg=0.69, std=0.00, steps=2.007e+08
2023-07-07 16:48:46,095 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9900, best=0.70, avg=0.69, std=0.00, steps=2.028e+08
2023-07-07 16:48:59,226 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10000, best=0.70, avg=0.69, std=0.00, steps=2.048e+08
2023-07-07 16:49:12,353 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10100, best=0.70, avg=0.69, std=0.00, steps=2.069e+08
2023-07-07 16:49:25,499 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10200, best=0.70, avg=0.69, std=0.00, steps=2.089e+08
2023-07-07 16:49:38,628 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10300, best=0.70, avg=0.69, std=0.00, steps=2.110e+08
2023-07-07 16:49:51,806 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10400, best=0.70, avg=0.69, std=0.00, steps=2.130e+08
2023-07-07 16:50:04,983 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10500, best=0.70, avg=0.70, std=0.00, steps=2.151e+08
2023-07-07 16:50:18,139 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10600, best=0.71, avg=0.69, std=0.00, steps=2.171e+08
2023-07-07 16:50:31,280 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10700, best=0.70, avg=0.70, std=0.00, steps=2.192e+08
2023-07-07 16:50:44,416 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10800, best=0.70, avg=0.70, std=0.00, steps=2.212e+08
2023-07-07 16:50:57,555 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10900, best=0.70, avg=0.70, std=0.00, steps=2.233e+08
2023-07-07 16:51:10,674 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11000, best=0.70, avg=0.70, std=0.00, steps=2.253e+08
2023-07-07 16:51:23,797 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11100, best=0.71, avg=0.70, std=0.00, steps=2.273e+08
2023-07-07 16:51:36,924 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11200, best=0.70, avg=0.70, std=0.00, steps=2.294e+08
2023-07-07 16:51:50,040 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11300, best=0.70, avg=0.70, std=0.00, steps=2.314e+08
2023-07-07 16:52:03,162 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11400, best=0.71, avg=0.70, std=0.00, steps=2.335e+08
2023-07-07 16:52:16,333 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11500, best=0.71, avg=0.70, std=0.00, steps=2.355e+08
2023-07-07 16:52:29,480 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11600, best=0.71, avg=0.70, std=0.00, steps=2.376e+08
2023-07-07 16:52:42,646 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11700, best=0.71, avg=0.70, std=0.00, steps=2.396e+08
2023-07-07 16:52:55,804 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11800, best=0.71, avg=0.70, std=0.00, steps=2.417e+08
2023-07-07 16:53:08,948 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11900, best=0.71, avg=0.70, std=0.00, steps=2.437e+08
2023-07-07 16:53:21,949 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11999, best=0.71, avg=0.70, std=0.00, steps=2.458e+08
2023-07-07 16:53:21,950 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 16:53:21,975 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:53:21,975 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:53:22,006 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:53:39,394 -        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 16:53:55,098 -        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 16:54:10,800 -        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 16:54:26,505 -        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 16:54:42,192 -        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 16:54:57,918 -        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 16:55:13,624 -        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 16:55:29,325 -        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 16:55:45,017 -        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 16:56:00,705 -        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 16:56:16,402 -        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 16:56:32,066 -        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 16:56:47,739 -        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 16:57:03,431 -        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 16:57:19,134 -        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 16:57:34,833 -        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 16:57:50,559 -        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 16:58:06,259 -        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 16:58:21,952 -        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 16:58:37,667 -        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 16:58:53,353 -        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 16:59:09,054 -        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 16:59:24,741 -        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 16:59:40,448 -        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 16:59:56,160 -        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 17:00:11,867 -        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 17:00:27,567 -        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 17:00:43,315 -        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 17:00:59,025 -        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 17:01:14,711 -        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 17:01:30,394 -        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 17:01:46,085 -        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 17:02:01,791 -        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 17:02:17,486 -        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 17:02:33,173 -        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 17:02:48,875 -        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 17:03:04,575 -        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 17:03:20,276 -        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 17:03:35,959 -        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 17:03:51,655 -        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 17:04:07,338 -        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 17:04:23,030 -        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 17:04:38,716 -        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 17:04:54,421 -        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 17:05:10,103 -        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 17:05:25,787 -        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 17:05:41,479 -        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 17:05:57,166 -        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 17:06:12,861 -        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 17:06:28,558 -        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 17:06:44,316 -        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 17:07:00,023 -        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 17:07:15,739 -        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 17:07:31,438 -        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 17:07:47,140 -        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 17:08:02,973 -        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 17:08:18,690 -        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 17:08:34,461 -        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 17:08:50,207 -        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 17:09:06,012 -        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 17:09:21,703 -        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 17:09:37,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.524e+08
2023-07-07 17:09:53,089 -        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 17:10:08,780 -        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 17:10:24,504 -        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 17:10:40,226 -        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 17:10:55,942 -        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 17:11:11,651 -        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 17:11:27,362 -        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 17:11:43,066 -        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 17:11:58,752 -        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 17:12:14,434 -        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 17:12:30,129 -        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 17:12:45,829 -        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 17:13:01,545 -        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 17:13:17,252 -        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 17:13:32,950 -        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 17:13:48,634 -        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 17:14:04,324 -        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 17:14:20,073 -        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 17:14:35,838 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 17:14:51,552 -        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 17:15:07,230 -        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 17:15:22,926 -        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 17:15:38,628 -        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 17:15:54,323 -        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 17:16:09,994 -        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 17:16:25,669 -        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 17:16:41,472 -        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 17:16:57,194 -        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 17:17:12,896 -        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 17:17:28,602 -        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 17:17:44,322 -        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 17:18:00,025 -        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 17:18:15,712 -        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 17:18:31,428 -        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 17:18:47,134 -        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 17:19:02,865 -        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 17:19:18,646 -        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 17:19:34,373 -        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 17:19:50,189 -        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 17:20:05,882 -        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 17:20:21,601 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10300, best=0.57, avg=0.56, std=0.00, steps=2.532e+08
2023-07-07 17:20:37,394 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10400, best=0.57, avg=0.57, std=0.00, steps=2.556e+08
2023-07-07 17:20:53,123 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10500, best=0.58, avg=0.57, std=0.00, steps=2.581e+08
2023-07-07 17:21:08,834 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10600, best=0.58, avg=0.57, std=0.00, steps=2.605e+08
2023-07-07 17:21:24,524 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10700, best=0.58, avg=0.57, std=0.00, steps=2.630e+08
2023-07-07 17:21:40,229 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10800, best=0.59, avg=0.58, std=0.00, steps=2.654e+08
2023-07-07 17:21:56,095 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10900, best=0.59, avg=0.59, std=0.00, steps=2.679e+08
2023-07-07 17:22:11,802 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11000, best=0.60, avg=0.59, std=0.00, steps=2.704e+08
2023-07-07 17:22:27,496 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11100, best=0.60, avg=0.59, std=0.00, steps=2.728e+08
2023-07-07 17:22:43,213 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11200, best=0.60, avg=0.59, std=0.00, steps=2.753e+08
2023-07-07 17:22:58,914 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11300, best=0.60, avg=0.59, std=0.00, steps=2.777e+08
2023-07-07 17:23:14,603 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11400, best=0.60, avg=0.60, std=0.00, steps=2.802e+08
2023-07-07 17:23:30,304 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11500, best=0.60, avg=0.60, std=0.00, steps=2.826e+08
2023-07-07 17:23:46,111 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11600, best=0.60, avg=0.60, std=0.00, steps=2.851e+08
2023-07-07 17:24:01,812 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11700, best=0.61, avg=0.60, std=0.00, steps=2.876e+08
2023-07-07 17:24:17,528 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11800, best=0.61, avg=0.60, std=0.00, steps=2.900e+08
2023-07-07 17:24:33,266 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11900, best=0.61, avg=0.60, std=0.00, steps=2.925e+08
2023-07-07 17:24:48,916 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11999, best=0.61, avg=0.60, std=0.00, steps=2.949e+08
2023-07-07 17:24:48,917 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 17:24:48,943 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 17:24:48,944 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 17:24:48,976 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 17:25:11,677 -        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 17:25:32,560 -        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 17:25:53,464 -        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 17:26:14,327 -        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 17:26:35,219 -        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 17:26:56,109 -        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 17:27:16,971 -        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 17:27:37,847 -        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 17:27:58,721 -        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 17:28:19,606 -        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 17:28:40,479 -        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 17:29:01,332 -        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 17:29:22,207 -        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 17:29:43,078 -        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 17:30:03,960 -        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 17:30:24,821 -        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 17:30:45,685 -        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 17:31:06,554 -        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 17:31:27,418 -        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 17:31:48,282 -        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 17:32:09,139 -        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 17:32:29,990 -        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 17:32:50,841 -        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 17:33:11,734 -        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 17:33:32,600 -        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 17:33:53,489 -        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 17:34:14,369 -        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 17:34:35,229 -        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 17:34:56,111 -        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 17:35:16,991 -        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 17:35:37,864 -        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 17:35:58,758 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 17:36:19,667 -        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 17:36:40,564 -        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 17:37:01,454 -        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 17:37:22,346 -        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 17:37:43,197 -        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 17:38:04,055 -        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 17:38:24,904 -        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 17:38:45,799 -        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 17:39:06,687 -        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 17:39:27,557 -        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 17:39:48,446 -        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 17:40:09,324 -        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 17:40:30,207 -        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 17:40:51,085 -        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 17:41:11,945 -        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 17:41:32,807 -        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 17:41:53,650 -        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 17:42:14,499 -        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 17:42:35,370 -        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 17:42:56,240 -        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 17:43:17,085 -        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 17:43:37,939 -        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 17:43:58,795 -        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 17:44:19,670 -        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 17:44:40,538 -        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 17:45:01,398 -        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 17:45:22,268 -        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 17:45:43,170 -        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 17:46:04,068 -        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 17:46:24,964 -        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 17:46:45,836 -        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 17:47:06,702 -        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 17:47:27,554 -        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 17:47:48,409 -        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 17:48:09,263 -        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 17:48:30,129 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6800, best=0.50, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 17:48:50,971 -        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 17:49:11,827 -        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 17:49:32,705 -        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 17:49:53,573 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7200, best=0.50, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 17:50:14,445 -        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 17:50:35,366 -        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 17:50:56,281 -        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 17:51:17,151 -        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 17:51:38,033 -        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 17:51:58,881 -        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 17:52:19,736 -        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 17:52:40,600 -        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 17:53:01,451 -        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 17:53:22,287 -        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 17:53:43,153 -        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 17:54:04,014 -        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 17:54:24,881 -        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 17:54:45,736 -        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 17:55:06,605 -        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 17:55:27,449 -        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 17:55:48,317 -        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 17:56:09,161 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9000, best=0.56, avg=0.55, std=0.00, steps=2.949e+08
2023-07-07 17:56:29,998 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9100, best=0.57, avg=0.56, std=0.00, steps=2.982e+08
2023-07-07 17:56:50,828 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9200, best=0.58, avg=0.57, std=0.00, steps=3.015e+08
2023-07-07 17:57:11,689 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9300, best=0.58, avg=0.57, std=0.00, steps=3.048e+08
2023-07-07 17:57:32,562 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9400, best=0.58, avg=0.58, std=0.00, steps=3.081e+08
2023-07-07 17:57:53,413 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9500, best=0.59, avg=0.59, std=0.00, steps=3.113e+08
2023-07-07 17:58:14,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9600, best=0.60, avg=0.59, std=0.00, steps=3.146e+08
2023-07-07 17:58:35,120 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9700, best=0.60, avg=0.60, std=0.00, steps=3.179e+08
2023-07-07 17:58:55,965 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9800, best=0.60, avg=0.60, std=0.00, steps=3.212e+08
2023-07-07 17:59:16,822 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9900, best=0.60, avg=0.60, std=0.00, steps=3.244e+08
2023-07-07 17:59:37,688 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10000, best=0.61, avg=0.60, std=0.00, steps=3.277e+08
2023-07-07 17:59:58,531 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10100, best=0.61, avg=0.60, std=0.00, steps=3.310e+08
2023-07-07 18:00:19,385 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10200, best=0.61, avg=0.61, std=0.00, steps=3.343e+08
2023-07-07 18:00:40,226 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10300, best=0.61, avg=0.61, std=0.00, steps=3.375e+08
2023-07-07 18:01:01,074 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10400, best=0.62, avg=0.61, std=0.00, steps=3.408e+08
2023-07-07 18:01:21,925 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10500, best=0.62, avg=0.61, std=0.00, steps=3.441e+08
2023-07-07 18:01:42,769 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10600, best=0.62, avg=0.61, std=0.00, steps=3.474e+08
2023-07-07 18:02:03,621 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10700, best=0.62, avg=0.62, std=0.00, steps=3.507e+08
2023-07-07 18:02:24,478 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10800, best=0.62, avg=0.62, std=0.00, steps=3.539e+08
2023-07-07 18:02:45,326 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10900, best=0.62, avg=0.62, std=0.00, steps=3.572e+08
2023-07-07 18:03:06,186 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11000, best=0.62, avg=0.62, std=0.00, steps=3.605e+08
2023-07-07 18:03:27,057 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11100, best=0.63, avg=0.62, std=0.00, steps=3.638e+08
2023-07-07 18:03:47,915 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11200, best=0.63, avg=0.62, std=0.00, steps=3.670e+08
2023-07-07 18:04:08,779 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11300, best=0.63, avg=0.62, std=0.00, steps=3.703e+08
2023-07-07 18:04:29,640 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11400, best=0.63, avg=0.62, std=0.00, steps=3.736e+08
2023-07-07 18:04:50,525 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11500, best=0.63, avg=0.63, std=0.00, steps=3.769e+08
2023-07-07 18:05:11,357 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11600, best=0.63, avg=0.63, std=0.00, steps=3.801e+08
2023-07-07 18:05:32,186 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11700, best=0.63, avg=0.63, std=0.00, steps=3.834e+08
2023-07-07 18:05:53,080 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11800, best=0.63, avg=0.63, std=0.00, steps=3.867e+08
2023-07-07 18:06:13,955 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11900, best=0.63, avg=0.63, std=0.00, steps=3.900e+08
2023-07-07 18:06:34,638 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11999, best=0.63, avg=0.63, std=0.00, steps=3.932e+08
2023-07-07 18:06:34,639 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 18:06:34,665 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:06:34,665 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:06:34,699 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:06:58,648 -        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 18:07:20,771 -        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 18:07:42,907 -        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 18:08:05,045 -        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 18:08:27,157 -        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 18:08:49,270 -        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 18:09:11,391 -        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 18:09:33,508 -        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 18:09:55,613 -        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 18:10:17,757 -        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 18:10:39,872 -        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 18:11:02,007 -        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 18:11:24,104 -        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 18:11:46,201 -        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 18:12:08,299 -        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 18:12:30,416 -        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 18:12:52,523 -        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 18:13:14,629 -        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 18:13:36,726 -        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 18:13:58,831 -        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 18:14:20,960 -        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 18:14:43,091 -        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 18:15:05,186 -        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 18:15:27,283 -        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 18:15:49,372 -        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 18:16:11,495 -        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 18:16:33,597 -        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 18:16:55,718 -        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 18:17:17,853 -        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 18:17:39,998 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3000, best=0.50, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 18:18:02,113 -        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 18:18:24,238 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 18:18:46,403 -        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 18:19:08,505 -        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 18:19:30,616 -        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 18:19:52,738 -        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 18:20:14,859 -        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 18:20:36,959 -        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 18:20:59,079 -        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 18:21:21,201 -        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 18:21:43,316 -        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 18:22:05,445 -        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 18:22:27,584 -        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 18:22:49,723 -        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 18:23:11,830 -        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 18:23:33,938 -        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 18:23:56,069 -        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 18:24:18,172 -        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 18:24:40,255 -        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 18:25:02,353 -        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 18:25:24,482 -        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 18:25:46,606 -        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 18:26:08,721 -        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 18:26:30,822 -        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 18:26:52,930 -        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 18:27:15,066 -        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 18:27:37,184 -        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 18:27:59,305 -        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 18:28:21,416 -        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 18:28:43,548 -        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 18:29:05,655 -        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 18:29:27,770 -        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 18:29:49,877 -        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 18:30:11,999 -        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 18:30:34,114 -        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 18:30:56,209 -        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 18:31:18,309 -        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 18:31:40,402 -        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 18:32:02,528 -        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 18:32:24,640 -        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 18:32:46,752 -        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 18:33:08,858 -        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 18:33:30,949 -        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 18:33:53,053 -        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 18:34:15,155 -        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 18:34:37,248 -        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 18:34:59,374 -        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 18:35:21,471 -        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 18:35:43,576 -        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 18:36:05,668 -        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 18:36:27,785 -        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 18:36:49,883 -        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 18:37:12,002 -        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 18:37:34,132 -        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 18:37:56,240 -        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 18:38:18,364 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8600, best=0.53, avg=0.52, std=0.00, steps=2.995e+08
2023-07-07 18:38:40,453 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8700, best=0.56, avg=0.55, std=0.00, steps=3.029e+08
2023-07-07 18:39:02,590 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8800, best=0.57, avg=0.56, std=0.00, steps=3.064e+08
2023-07-07 18:39:24,702 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8900, best=0.57, avg=0.57, std=0.00, steps=3.099e+08
2023-07-07 18:39:46,821 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9000, best=0.58, avg=0.57, std=0.00, steps=3.134e+08
2023-07-07 18:40:08,939 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9100, best=0.58, avg=0.58, std=0.00, steps=3.169e+08
2023-07-07 18:40:31,058 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9200, best=0.59, avg=0.58, std=0.00, steps=3.203e+08
2023-07-07 18:40:53,151 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9300, best=0.59, avg=0.58, std=0.00, steps=3.238e+08
2023-07-07 18:41:15,271 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9400, best=0.59, avg=0.59, std=0.00, steps=3.273e+08
2023-07-07 18:41:37,391 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9500, best=0.60, avg=0.59, std=0.00, steps=3.308e+08
2023-07-07 18:41:59,521 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9600, best=0.60, avg=0.59, std=0.00, steps=3.343e+08
2023-07-07 18:42:21,630 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9700, best=0.60, avg=0.60, std=0.00, steps=3.378e+08
2023-07-07 18:42:43,739 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9800, best=0.60, avg=0.60, std=0.00, steps=3.412e+08
2023-07-07 18:43:05,853 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9900, best=0.60, avg=0.60, std=0.00, steps=3.447e+08
2023-07-07 18:43:27,967 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10000, best=0.61, avg=0.60, std=0.00, steps=3.482e+08
2023-07-07 18:43:50,065 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10100, best=0.61, avg=0.60, std=0.00, steps=3.517e+08
2023-07-07 18:44:12,170 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10200, best=0.61, avg=0.60, std=0.00, steps=3.552e+08
2023-07-07 18:44:34,308 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10300, best=0.61, avg=0.61, std=0.00, steps=3.586e+08
2023-07-07 18:44:56,407 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10400, best=0.61, avg=0.61, std=0.00, steps=3.621e+08
2023-07-07 18:45:18,549 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10500, best=0.62, avg=0.61, std=0.00, steps=3.656e+08
2023-07-07 18:45:40,707 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10600, best=0.62, avg=0.61, std=0.00, steps=3.691e+08
2023-07-07 18:46:02,819 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10700, best=0.62, avg=0.61, std=0.00, steps=3.726e+08
2023-07-07 18:46:24,985 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10800, best=0.62, avg=0.61, std=0.00, steps=3.760e+08
2023-07-07 18:46:47,135 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10900, best=0.62, avg=0.61, std=0.00, steps=3.795e+08
2023-07-07 18:47:09,234 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11000, best=0.62, avg=0.61, std=0.00, steps=3.830e+08
2023-07-07 18:47:31,349 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11100, best=0.62, avg=0.61, std=0.00, steps=3.865e+08
2023-07-07 18:47:53,442 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11200, best=0.62, avg=0.61, std=0.00, steps=3.900e+08
2023-07-07 18:48:15,530 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11300, best=0.62, avg=0.62, std=0.00, steps=3.935e+08
2023-07-07 18:48:37,613 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11400, best=0.62, avg=0.62, std=0.00, steps=3.969e+08
2023-07-07 18:48:59,691 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11500, best=0.62, avg=0.62, std=0.00, steps=4.004e+08
2023-07-07 18:49:21,787 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11600, best=0.62, avg=0.62, std=0.00, steps=4.039e+08
2023-07-07 18:49:43,925 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11700, best=0.62, avg=0.62, std=0.00, steps=4.074e+08
2023-07-07 18:50:06,058 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11800, best=0.62, avg=0.62, std=0.00, steps=4.109e+08
2023-07-07 18:50:28,213 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11900, best=0.62, avg=0.62, std=0.00, steps=4.143e+08
2023-07-07 18:50:50,123 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11999, best=0.63, avg=0.62, std=0.00, steps=4.178e+08
2023-07-07 18:50:50,124 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 18:50:50,149 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:50:50,149 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:50:50,183 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:51:15,408 -        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 18:51:38,800 -        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 18:52:02,199 -        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 18:52:25,588 -        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 18:52:48,969 -        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 18:53:12,380 -        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 18:53:35,788 -        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 18:53:59,187 -        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 18:54:22,603 -        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 18:54:46,008 -        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 18:55:09,400 -        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 18:55:32,797 -        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 18:55:56,196 -        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 18:56:19,575 -        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 18:56:42,969 -        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 18:57:06,336 -        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 18:57:29,744 -        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 18:57:53,153 -        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 18:58:16,556 -        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 18:58:39,943 -        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 18:59:03,335 -        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 18:59:26,730 -        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 18:59:50,117 -        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 19:00:13,499 -        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 19:00:36,876 -        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 19:01:00,256 -        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 19:01:23,651 -        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 19:01:47,040 -        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 19:02:10,471 -        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 19:02:33,899 -        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 19:02:57,300 -        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 19:03:20,673 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 19:03:44,053 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3300, best=0.50, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 19:04:07,458 -        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 19:04:30,850 -        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 19:04:54,294 -        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 19:05:17,674 -        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 19:05:41,077 -        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 19:06:04,466 -        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 19:06:27,850 -        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 19:06:51,255 -        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 19:07:14,632 -        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 19:07:38,036 -        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 19:08:01,429 -        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 19:08:24,796 -        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 19:08:48,184 -        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 19:09:11,560 -        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 19:09:34,924 -        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 19:09:58,330 -        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 19:10:21,725 -        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 19:10:45,118 -        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 19:11:08,526 -        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 19:11:31,917 -        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 19:11:55,320 -        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 19:12:18,737 -        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 19:12:42,147 -        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 19:13:05,548 -        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 19:13:28,922 -        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 19:13:52,296 -        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 19:14:15,681 -        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 19:14:39,083 -        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 19:15:02,497 -        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 19:15:25,888 -        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 19:15:49,258 -        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 19:16:12,618 -        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 19:16:35,995 -        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 19:16:59,379 -        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 19:17:22,762 -        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 19:17:46,151 -        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 19:18:09,551 -        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 19:18:32,921 -        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 19:18:56,297 -        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 19:19:19,653 -        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 19:19:43,021 -        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 19:20:06,392 -        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 19:20:29,777 -        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 19:20:53,148 -        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 19:21:16,523 -        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 19:21:39,910 -        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 19:22:03,295 -        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 19:22:26,700 -        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 19:22:50,065 -        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 19:23:13,455 -        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 19:23:36,835 -        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 19:24:00,231 -        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 19:24:23,603 -        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 19:24:46,995 -        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 19:25:10,382 -        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 19:25:33,751 -        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 19:25:57,127 -        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 19:26:20,532 -        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 19:26:43,905 -        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 19:27:07,263 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9300, best=0.50, avg=0.50, std=0.00, steps=3.429e+08
2023-07-07 19:27:30,652 -        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 19:27:54,025 -        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 19:28:17,396 -        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 19:28:40,782 -        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 19:29:04,161 -        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 19:29:27,558 -        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 19:29:50,923 -        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 19:30:14,291 -        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 19:30:37,668 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10200, best=0.56, avg=0.55, std=0.00, steps=3.760e+08
2023-07-07 19:31:01,043 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10300, best=0.56, avg=0.55, std=0.00, steps=3.797e+08
2023-07-07 19:31:24,427 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10400, best=0.56, avg=0.56, std=0.00, steps=3.834e+08
2023-07-07 19:31:47,815 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10500, best=0.57, avg=0.56, std=0.00, steps=3.871e+08
2023-07-07 19:32:11,231 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10600, best=0.57, avg=0.57, std=0.00, steps=3.908e+08
2023-07-07 19:32:34,617 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10700, best=0.58, avg=0.57, std=0.00, steps=3.945e+08
2023-07-07 19:32:58,019 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10800, best=0.58, avg=0.57, std=0.00, steps=3.982e+08
2023-07-07 19:33:21,429 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10900, best=0.58, avg=0.58, std=0.00, steps=4.019e+08
2023-07-07 19:33:44,813 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11000, best=0.58, avg=0.58, std=0.00, steps=4.055e+08
2023-07-07 19:34:08,193 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11100, best=0.59, avg=0.58, std=0.00, steps=4.092e+08
2023-07-07 19:34:31,555 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11200, best=0.59, avg=0.58, std=0.00, steps=4.129e+08
2023-07-07 19:34:54,948 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11300, best=0.59, avg=0.58, std=0.00, steps=4.166e+08
2023-07-07 19:35:18,348 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11400, best=0.59, avg=0.59, std=0.00, steps=4.203e+08
2023-07-07 19:35:41,745 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11500, best=0.59, avg=0.59, std=0.00, steps=4.240e+08
2023-07-07 19:36:05,145 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11600, best=0.59, avg=0.59, std=0.00, steps=4.277e+08
2023-07-07 19:36:28,530 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11700, best=0.59, avg=0.59, std=0.00, steps=4.313e+08
2023-07-07 19:36:51,909 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11800, best=0.59, avg=0.59, std=0.00, steps=4.350e+08
2023-07-07 19:37:15,306 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11900, best=0.60, avg=0.59, std=0.00, steps=4.387e+08
2023-07-07 19:37:38,473 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11999, best=0.60, avg=0.59, std=0.00, steps=4.424e+08
2023-07-07 19:37:38,474 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
2023-07-07 19:37:38,500 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 19:37:38,500 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 19:37:38,532 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 19:38:06,321 -        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 19:38:32,253 -        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 19:38:58,170 -        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 19:39:24,133 -        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 19:39:50,072 -        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 19:40:16,014 -        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 19:40:41,962 -        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 19:41:07,906 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 800, best=0.50, avg=0.50, std=0.00, steps=3.281e+07
2023-07-07 19:41:33,876 -        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 19:41:59,815 -        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 19:42:25,755 -        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 19:42:51,721 -        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 19:43:17,690 -        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 19:43:43,628 -        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 19:44:09,566 -        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 19:44:35,522 -        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 19:45:01,495 -        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 19:45:27,442 -        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 19:45:53,376 -        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 19:46:19,322 -        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 19:46:45,248 -        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 19:47:11,169 -        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 19:47:37,104 -        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 19:48:03,055 -        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 19:48:29,010 -        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 19:48:54,958 -        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 19:49:20,922 -        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 19:49:46,859 -        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 19:50:12,785 -        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 19:50:38,779 -        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 19:51:04,748 -        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 19:51:30,686 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 19:51:56,629 -        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 19:52:22,556 -        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 19:52:48,478 -        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 19:53:14,409 -        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 19:53:40,342 -        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 19:54:06,307 -        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 19:54:32,247 -        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 19:54:58,190 -        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 19:55:24,139 -        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 19:55:50,106 -        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 19:56:16,076 -        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 19:56:42,006 -        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 19:57:07,940 -        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 19:57:33,892 -        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 19:57:59,806 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4700, best=0.50, avg=0.50, std=0.00, steps=1.926e+08
2023-07-07 19:58:25,729 -        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 19:58:51,674 -        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 19:59:17,613 -        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 19:59:43,555 -        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 20:00:09,484 -        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 20:00:35,421 -        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 20:01:01,381 -        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 20:01:27,311 -        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 20:01:53,245 -        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 20:02:19,189 -        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 20:02:45,195 -        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 20:03:11,137 -        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 20:03:37,071 -        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 20:04:03,001 -        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 20:04:28,951 -        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 20:04:54,898 -        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 20:05:20,823 -        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 20:05:46,760 -        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 20:06:12,697 -        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 20:06:38,622 -        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 20:07:04,542 -        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 20:07:30,475 -        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 20:07:56,436 -        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 20:08:22,390 -        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 20:08:48,348 -        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 20:09:14,272 -        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 20:09:40,227 -        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 20:10:06,161 -        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 20:10:32,085 -        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 20:10:58,028 -        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 20:11:23,958 -        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 20:11:49,900 -        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 20:12:15,836 -        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 20:12:41,769 -        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 20:13:07,717 -        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 20:13:33,663 -        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 20:13:59,635 -        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 20:14:25,578 -        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 20:14:51,520 -        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 20:15:17,542 -        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 20:15:43,489 -        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 20:16:09,428 -        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 20:16:35,389 -        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 20:17:01,343 -        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 20:17:27,315 -        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 20:17:53,268 -        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 20:18:19,224 -        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 20:18:45,208 -        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 20:19:11,154 -        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 20:19:37,088 -        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 20:20:03,058 -        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 20:20:29,019 -        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 20:20:54,954 -        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 20:21:20,906 -        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 20:21:46,847 -        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 20:22:12,789 -        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 20:22:38,754 -        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 20:23:04,735 -        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 20:23:30,691 -        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 20:23:56,630 -        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 20:24:22,611 -        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 20:24:48,568 -        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 20:25:14,532 -        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 20:25:40,495 -        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 20:26:06,431 -        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 20:26:32,363 -        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 20:26:58,317 -        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 20:27:24,273 -        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 20:27:50,209 -        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 20:28:16,162 -        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 20:28:42,121 -        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 20:29:08,087 -        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 20:29:33,775 -        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 20:29:33,776 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135926
