2023-07-07 13:59:34,648 -        meta learning: [    INFO] - [INFO] checkpoint saved to: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 13:59:34,648 -        meta learning: [    INFO] - [INFO] tensorboard dir set to: ./runs/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 13:59:34,648 -        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=50, 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--20230707-135934', summary_writer=<torch.utils.tensorboard.writer.SummaryWriter object at 0x7fe03067fd90>, tb_prefix='PGPE/SeqTask/GruPolicy')
2023-07-07 13:59:38,109 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:59:38,110 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:59:38,185 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:59:44,454 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 100, best=0.75, avg=0.73, std=0.01, steps=4.137e+05
2023-07-07 13:59:47,340 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 200, best=0.80, avg=0.79, std=0.01, steps=8.233e+05
2023-07-07 13:59:50,209 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 300, best=0.86, avg=0.84, std=0.01, steps=1.233e+06
2023-07-07 13:59:53,072 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 400, best=0.89, avg=0.88, std=0.00, steps=1.642e+06
2023-07-07 13:59:55,927 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 500, best=0.91, avg=0.90, std=0.00, steps=2.052e+06
2023-07-07 13:59:58,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 600, best=0.93, avg=0.92, std=0.00, steps=2.462e+06
2023-07-07 14:00:01,638 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 700, best=0.94, avg=0.93, std=0.00, steps=2.871e+06
2023-07-07 14:00:04,503 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 800, best=0.95, avg=0.94, std=0.00, steps=3.281e+06
2023-07-07 14:00:07,385 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 900, best=0.96, avg=0.95, std=0.00, steps=3.690e+06
2023-07-07 14:00:10,257 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1000, best=0.96, avg=0.95, std=0.00, steps=4.100e+06
2023-07-07 14:00:13,141 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1100, best=0.96, avg=0.95, std=0.00, steps=4.510e+06
2023-07-07 14:00:16,026 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1200, best=0.96, avg=0.95, std=0.00, steps=4.919e+06
2023-07-07 14:00:18,897 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1300, best=0.96, avg=0.95, std=0.00, steps=5.329e+06
2023-07-07 14:00:21,780 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1400, best=0.96, avg=0.95, std=0.00, steps=5.738e+06
2023-07-07 14:00:24,644 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1500, best=0.96, avg=0.95, std=0.00, steps=6.148e+06
2023-07-07 14:00:27,528 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1600, best=0.96, avg=0.95, std=0.00, steps=6.558e+06
2023-07-07 14:00:30,400 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1700, best=0.96, avg=0.95, std=0.00, steps=6.967e+06
2023-07-07 14:00:33,268 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1800, best=0.96, avg=0.95, std=0.00, steps=7.377e+06
2023-07-07 14:00:36,146 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1900, best=0.96, avg=0.95, std=0.00, steps=7.786e+06
2023-07-07 14:00:39,012 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2000, best=0.96, avg=0.95, std=0.00, steps=8.196e+06
2023-07-07 14:00:41,882 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2100, best=0.96, avg=0.95, std=0.00, steps=8.606e+06
2023-07-07 14:00:44,766 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2200, best=0.96, avg=0.95, std=0.00, steps=9.015e+06
2023-07-07 14:00:47,645 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2300, best=0.96, avg=0.95, std=0.00, steps=9.425e+06
2023-07-07 14:00:50,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2400, best=0.96, avg=0.95, std=0.00, steps=9.834e+06
2023-07-07 14:00:53,385 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2500, best=0.96, avg=0.95, std=0.00, steps=1.024e+07
2023-07-07 14:00:56,255 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2600, best=0.96, avg=0.95, std=0.00, steps=1.065e+07
2023-07-07 14:00:59,114 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2700, best=0.96, avg=0.95, std=0.00, steps=1.106e+07
2023-07-07 14:01:01,976 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2800, best=0.96, avg=0.95, std=0.00, steps=1.147e+07
2023-07-07 14:01:04,838 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2900, best=0.96, avg=0.95, std=0.00, steps=1.188e+07
2023-07-07 14:01:07,694 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3000, best=0.96, avg=0.95, std=0.00, steps=1.229e+07
2023-07-07 14:01:10,559 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3100, best=0.96, avg=0.95, std=0.00, steps=1.270e+07
2023-07-07 14:01:13,427 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3200, best=0.96, avg=0.95, std=0.00, steps=1.311e+07
2023-07-07 14:01:16,301 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3300, best=0.96, avg=0.95, std=0.00, steps=1.352e+07
2023-07-07 14:01:19,174 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3400, best=0.96, avg=0.95, std=0.00, steps=1.393e+07
2023-07-07 14:01:22,062 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3500, best=0.96, avg=0.95, std=0.00, steps=1.434e+07
2023-07-07 14:01:24,953 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3600, best=0.96, avg=0.95, std=0.00, steps=1.475e+07
2023-07-07 14:01:27,837 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3700, best=0.96, avg=0.95, std=0.00, steps=1.516e+07
2023-07-07 14:01:30,725 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3800, best=0.96, avg=0.95, std=0.00, steps=1.557e+07
2023-07-07 14:01:33,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3900, best=0.96, avg=0.95, std=0.00, steps=1.598e+07
2023-07-07 14:01:36,519 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4000, best=0.96, avg=0.95, std=0.00, steps=1.639e+07
2023-07-07 14:01:39,408 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4100, best=0.96, avg=0.95, std=0.00, steps=1.680e+07
2023-07-07 14:01:42,302 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4200, best=0.96, avg=0.95, std=0.00, steps=1.721e+07
2023-07-07 14:01:45,194 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4300, best=0.96, avg=0.95, std=0.00, steps=1.762e+07
2023-07-07 14:01:48,082 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4400, best=0.96, avg=0.95, std=0.00, steps=1.803e+07
2023-07-07 14:01:50,974 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4500, best=0.96, avg=0.95, std=0.00, steps=1.844e+07
2023-07-07 14:01:53,847 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4600, best=0.96, avg=0.95, std=0.00, steps=1.885e+07
2023-07-07 14:01:56,741 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4700, best=0.96, avg=0.95, std=0.00, steps=1.926e+07
2023-07-07 14:01:59,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4800, best=0.96, avg=0.95, std=0.00, steps=1.966e+07
2023-07-07 14:02:02,499 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4900, best=0.96, avg=0.95, std=0.00, steps=2.007e+07
2023-07-07 14:02:05,367 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5000, best=0.96, avg=0.95, std=0.00, steps=2.048e+07
2023-07-07 14:02:08,237 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5100, best=0.96, avg=0.95, std=0.00, steps=2.089e+07
2023-07-07 14:02:11,119 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5200, best=0.96, avg=0.95, std=0.00, steps=2.130e+07
2023-07-07 14:02:14,014 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5300, best=0.98, avg=0.98, std=0.00, steps=2.171e+07
2023-07-07 14:02:16,910 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5400, best=0.99, avg=0.98, std=0.00, steps=2.212e+07
2023-07-07 14:02:19,811 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5500, best=0.99, avg=0.99, std=0.00, steps=2.253e+07
2023-07-07 14:02:22,690 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5600, best=0.99, avg=0.99, std=0.00, steps=2.294e+07
2023-07-07 14:02:25,581 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5700, best=0.99, avg=0.99, std=0.00, steps=2.335e+07
2023-07-07 14:02:28,472 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5800, best=1.00, avg=0.99, std=0.00, steps=2.376e+07
2023-07-07 14:02:31,344 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5900, best=1.00, avg=0.99, std=0.00, steps=2.417e+07
2023-07-07 14:02:34,228 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6000, best=1.00, avg=0.99, std=0.00, steps=2.458e+07
2023-07-07 14:02:37,099 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6100, best=0.99, avg=0.99, std=0.00, steps=2.499e+07
2023-07-07 14:02:39,975 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6200, best=1.00, avg=0.99, std=0.00, steps=2.540e+07
2023-07-07 14:02:42,839 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6300, best=0.99, avg=0.99, std=0.00, steps=2.581e+07
2023-07-07 14:02:45,715 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6400, best=1.00, avg=0.99, std=0.00, steps=2.622e+07
2023-07-07 14:02:48,613 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6500, best=1.00, avg=0.99, std=0.00, steps=2.663e+07
2023-07-07 14:02:51,513 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6600, best=1.00, avg=1.00, std=0.00, steps=2.704e+07
2023-07-07 14:02:54,418 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6700, best=1.00, avg=1.00, std=0.00, steps=2.745e+07
2023-07-07 14:02:57,285 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6800, best=1.00, avg=1.00, std=0.00, steps=2.786e+07
2023-07-07 14:03:00,151 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6900, best=1.00, avg=1.00, std=0.00, steps=2.827e+07
2023-07-07 14:03:03,009 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7000, best=1.00, avg=1.00, std=0.00, steps=2.868e+07
2023-07-07 14:03:05,885 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7100, best=1.00, avg=1.00, std=0.00, steps=2.909e+07
2023-07-07 14:03:08,757 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7200, best=1.00, avg=1.00, std=0.00, steps=2.950e+07
2023-07-07 14:03:11,628 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7300, best=1.00, avg=1.00, std=0.00, steps=2.990e+07
2023-07-07 14:03:14,512 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7400, best=1.00, avg=1.00, std=0.00, steps=3.031e+07
2023-07-07 14:03:17,374 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7500, best=1.00, avg=1.00, std=0.00, steps=3.072e+07
2023-07-07 14:03:20,244 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7600, best=1.00, avg=1.00, std=0.00, steps=3.113e+07
2023-07-07 14:03:23,124 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7700, best=1.00, avg=1.00, std=0.00, steps=3.154e+07
2023-07-07 14:03:25,993 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7800, best=1.00, avg=1.00, std=0.00, steps=3.195e+07
2023-07-07 14:03:28,862 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7900, best=1.00, avg=1.00, std=0.00, steps=3.236e+07
2023-07-07 14:03:31,729 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8000, best=1.00, avg=1.00, std=0.00, steps=3.277e+07
2023-07-07 14:03:34,610 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8100, best=1.00, avg=1.00, std=0.00, steps=3.318e+07
2023-07-07 14:03:37,488 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8200, best=1.00, avg=1.00, std=0.00, steps=3.359e+07
2023-07-07 14:03:40,384 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8300, best=1.00, avg=1.00, std=0.00, steps=3.400e+07
2023-07-07 14:03:43,272 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8400, best=1.00, avg=1.00, std=0.00, steps=3.441e+07
2023-07-07 14:03:46,164 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8500, best=1.00, avg=1.00, std=0.00, steps=3.482e+07
2023-07-07 14:03:49,062 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8600, best=1.00, avg=1.00, std=0.00, steps=3.523e+07
2023-07-07 14:03:51,954 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8700, best=1.00, avg=1.00, std=0.00, steps=3.564e+07
2023-07-07 14:03:54,835 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8800, best=1.00, avg=1.00, std=0.00, steps=3.605e+07
2023-07-07 14:03:57,711 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8900, best=1.00, avg=1.00, std=0.00, steps=3.646e+07
2023-07-07 14:04:00,591 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9000, best=1.00, avg=1.00, std=0.00, steps=3.687e+07
2023-07-07 14:04:03,469 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9100, best=1.00, avg=1.00, std=0.00, steps=3.728e+07
2023-07-07 14:04:06,330 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9200, best=1.00, avg=1.00, std=0.00, steps=3.769e+07
2023-07-07 14:04:09,194 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9300, best=1.00, avg=1.00, std=0.00, steps=3.810e+07
2023-07-07 14:04:12,070 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9400, best=1.00, avg=1.00, std=0.00, steps=3.851e+07
2023-07-07 14:04:14,967 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9500, best=1.00, avg=1.00, std=0.00, steps=3.892e+07
2023-07-07 14:04:17,847 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9600, best=1.00, avg=1.00, std=0.00, steps=3.933e+07
2023-07-07 14:04:20,744 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9700, best=1.00, avg=1.00, std=0.00, steps=3.974e+07
2023-07-07 14:04:23,616 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9800, best=1.00, avg=1.00, std=0.00, steps=4.014e+07
2023-07-07 14:04:26,497 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9900, best=1.00, avg=1.00, std=0.00, steps=4.055e+07
2023-07-07 14:04:29,383 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10000, best=1.00, avg=1.00, std=0.00, steps=4.096e+07
2023-07-07 14:04:32,270 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10100, best=1.00, avg=1.00, std=0.00, steps=4.137e+07
2023-07-07 14:04:35,151 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10200, best=1.00, avg=1.00, std=0.00, steps=4.178e+07
2023-07-07 14:04:38,029 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10300, best=1.00, avg=1.00, std=0.00, steps=4.219e+07
2023-07-07 14:04:40,935 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10400, best=1.00, avg=1.00, std=0.00, steps=4.260e+07
2023-07-07 14:04:43,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10500, best=1.00, avg=1.00, std=0.00, steps=4.301e+07
2023-07-07 14:04:46,686 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10600, best=1.00, avg=1.00, std=0.00, steps=4.342e+07
2023-07-07 14:04:49,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10700, best=1.00, avg=1.00, std=0.00, steps=4.383e+07
2023-07-07 14:04:52,427 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10800, best=1.00, avg=1.00, std=0.00, steps=4.424e+07
2023-07-07 14:04:55,302 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 10900, best=1.00, avg=1.00, std=0.00, steps=4.465e+07
2023-07-07 14:04:58,173 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11000, best=1.00, avg=1.00, std=0.00, steps=4.506e+07
2023-07-07 14:05:01,052 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11100, best=1.00, avg=1.00, std=0.00, steps=4.547e+07
2023-07-07 14:05:03,962 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11200, best=1.00, avg=1.00, std=0.00, steps=4.588e+07
2023-07-07 14:05:06,838 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11300, best=1.00, avg=1.00, std=0.00, steps=4.629e+07
2023-07-07 14:05:09,697 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11400, best=1.00, avg=1.00, std=0.00, steps=4.670e+07
2023-07-07 14:05:12,587 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11500, best=1.00, avg=1.00, std=0.00, steps=4.711e+07
2023-07-07 14:05:15,466 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11600, best=1.00, avg=1.00, std=0.00, steps=4.752e+07
2023-07-07 14:05:18,349 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11700, best=1.00, avg=1.00, std=0.00, steps=4.793e+07
2023-07-07 14:05:21,251 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11800, best=1.00, avg=1.00, std=0.00, steps=4.834e+07
2023-07-07 14:05:24,140 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11900, best=1.00, avg=1.00, std=0.00, steps=4.875e+07
2023-07-07 14:05:27,004 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 11999, best=1.00, avg=1.00, std=0.00, steps=4.915e+07
2023-07-07 14:05:27,005 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 14:05:27,033 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:05:27,033 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:05:27,067 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:05:32,806 -        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 14:05:36,977 -        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 14:05:41,148 -        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 14:05:45,332 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 400, best=0.53, avg=0.50, std=0.01, steps=2.464e+06
2023-07-07 14:05:49,504 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=3.078e+06
2023-07-07 14:05:53,665 -        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 14:05:57,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 700, best=0.53, avg=0.50, std=0.01, steps=4.307e+06
2023-07-07 14:06:01,966 -        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 14:06:06,128 -        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 14:06:10,302 -        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 14:06:14,450 -        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 14:06:18,614 -        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 14:06:22,779 -        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 14:06:26,937 -        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 14:06:31,098 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1500, best=0.53, avg=0.50, std=0.01, steps=9.222e+06
2023-07-07 14:06:35,260 -        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 14:06:39,416 -        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 14:06:43,591 -        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 14:06:47,742 -        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 14:06:51,909 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2000, best=0.53, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 14:06:56,059 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2100, best=0.60, avg=0.58, std=0.01, steps=1.291e+07
2023-07-07 14:07:00,222 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2200, best=0.72, avg=0.70, std=0.01, steps=1.352e+07
2023-07-07 14:07:04,367 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2300, best=0.74, avg=0.72, std=0.01, steps=1.414e+07
2023-07-07 14:07:08,532 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2400, best=0.75, avg=0.74, std=0.01, steps=1.475e+07
2023-07-07 14:07:12,701 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2500, best=0.76, avg=0.75, std=0.01, steps=1.537e+07
2023-07-07 14:07:16,877 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2600, best=0.79, avg=0.76, std=0.01, steps=1.598e+07
2023-07-07 14:07:21,051 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2700, best=0.79, avg=0.78, std=0.01, steps=1.659e+07
2023-07-07 14:07:25,225 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2800, best=0.79, avg=0.78, std=0.01, steps=1.721e+07
2023-07-07 14:07:29,380 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2900, best=0.80, avg=0.78, std=0.01, steps=1.782e+07
2023-07-07 14:07:33,537 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3000, best=0.81, avg=0.79, std=0.01, steps=1.844e+07
2023-07-07 14:07:37,702 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3100, best=0.81, avg=0.80, std=0.01, steps=1.905e+07
2023-07-07 14:07:41,852 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3200, best=0.82, avg=0.81, std=0.01, steps=1.967e+07
2023-07-07 14:07:46,011 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3300, best=0.83, avg=0.82, std=0.01, steps=2.028e+07
2023-07-07 14:07:50,209 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3400, best=0.83, avg=0.82, std=0.00, steps=2.090e+07
2023-07-07 14:07:54,368 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3500, best=0.84, avg=0.83, std=0.01, steps=2.151e+07
2023-07-07 14:07:58,518 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3600, best=0.85, avg=0.84, std=0.01, steps=2.212e+07
2023-07-07 14:08:02,683 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3700, best=0.86, avg=0.85, std=0.00, steps=2.274e+07
2023-07-07 14:08:06,834 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3800, best=0.86, avg=0.85, std=0.01, steps=2.335e+07
2023-07-07 14:08:10,992 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3900, best=0.86, avg=0.85, std=0.00, steps=2.397e+07
2023-07-07 14:08:15,159 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4000, best=0.86, avg=0.85, std=0.00, steps=2.458e+07
2023-07-07 14:08:19,306 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4100, best=0.87, avg=0.86, std=0.00, steps=2.520e+07
2023-07-07 14:08:23,454 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4200, best=0.87, avg=0.86, std=0.00, steps=2.581e+07
2023-07-07 14:08:27,588 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4300, best=0.87, avg=0.86, std=0.00, steps=2.643e+07
2023-07-07 14:08:31,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4400, best=0.87, avg=0.86, std=0.00, steps=2.704e+07
2023-07-07 14:08:35,900 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4500, best=0.88, avg=0.86, std=0.00, steps=2.765e+07
2023-07-07 14:08:40,047 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4600, best=0.88, avg=0.87, std=0.00, steps=2.827e+07
2023-07-07 14:08:44,207 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4700, best=0.88, avg=0.87, std=0.00, steps=2.888e+07
2023-07-07 14:08:48,362 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4800, best=0.88, avg=0.87, std=0.00, steps=2.950e+07
2023-07-07 14:08:52,537 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4900, best=0.88, avg=0.87, std=0.00, steps=3.011e+07
2023-07-07 14:08:56,702 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5000, best=0.88, avg=0.87, std=0.00, steps=3.073e+07
2023-07-07 14:09:00,880 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5100, best=0.88, avg=0.87, std=0.00, steps=3.134e+07
2023-07-07 14:09:05,044 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5200, best=0.89, avg=0.87, std=0.00, steps=3.195e+07
2023-07-07 14:09:09,207 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5300, best=0.89, avg=0.87, std=0.00, steps=3.257e+07
2023-07-07 14:09:13,353 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5400, best=0.89, avg=0.88, std=0.00, steps=3.318e+07
2023-07-07 14:09:17,511 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5500, best=0.89, avg=0.88, std=0.00, steps=3.380e+07
2023-07-07 14:09:21,666 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5600, best=0.89, avg=0.88, std=0.00, steps=3.441e+07
2023-07-07 14:09:25,835 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5700, best=0.89, avg=0.88, std=0.00, steps=3.503e+07
2023-07-07 14:09:29,993 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5800, best=0.89, avg=0.88, std=0.00, steps=3.564e+07
2023-07-07 14:09:34,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5900, best=0.89, avg=0.88, std=0.00, steps=3.626e+07
2023-07-07 14:09:38,322 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6000, best=0.90, avg=0.89, std=0.00, steps=3.687e+07
2023-07-07 14:09:42,491 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6100, best=0.90, avg=0.89, std=0.00, steps=3.748e+07
2023-07-07 14:09:46,651 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6200, best=0.89, avg=0.89, std=0.00, steps=3.810e+07
2023-07-07 14:09:50,808 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6300, best=0.89, avg=0.89, std=0.00, steps=3.871e+07
2023-07-07 14:09:54,982 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6400, best=0.90, avg=0.89, std=0.00, steps=3.933e+07
2023-07-07 14:09:59,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6500, best=0.90, avg=0.89, std=0.00, steps=3.994e+07
2023-07-07 14:10:03,295 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6600, best=0.90, avg=0.89, std=0.00, steps=4.056e+07
2023-07-07 14:10:07,475 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6700, best=0.90, avg=0.89, std=0.00, steps=4.117e+07
2023-07-07 14:10:11,643 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6800, best=0.90, avg=0.89, std=0.00, steps=4.179e+07
2023-07-07 14:10:15,819 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6900, best=0.90, avg=0.89, std=0.00, steps=4.240e+07
2023-07-07 14:10:19,972 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7000, best=0.90, avg=0.89, std=0.00, steps=4.301e+07
2023-07-07 14:10:24,126 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7100, best=0.90, avg=0.89, std=0.00, steps=4.363e+07
2023-07-07 14:10:28,264 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7200, best=0.90, avg=0.89, std=0.00, steps=4.424e+07
2023-07-07 14:10:32,421 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7300, best=0.90, avg=0.89, std=0.00, steps=4.486e+07
2023-07-07 14:10:36,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7400, best=0.90, avg=0.89, std=0.00, steps=4.547e+07
2023-07-07 14:10:40,736 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7500, best=0.90, avg=0.89, std=0.00, steps=4.609e+07
2023-07-07 14:10:44,890 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7600, best=0.90, avg=0.89, std=0.00, steps=4.670e+07
2023-07-07 14:10:49,043 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7700, best=0.90, avg=0.89, std=0.00, steps=4.731e+07
2023-07-07 14:10:53,227 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7800, best=0.90, avg=0.89, std=0.00, steps=4.793e+07
2023-07-07 14:10:57,391 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7900, best=0.90, avg=0.89, std=0.00, steps=4.854e+07
2023-07-07 14:11:01,563 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8000, best=0.90, avg=0.89, std=0.00, steps=4.916e+07
2023-07-07 14:11:05,725 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8100, best=0.90, avg=0.89, std=0.00, steps=4.977e+07
2023-07-07 14:11:09,884 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8200, best=0.90, avg=0.89, std=0.00, steps=5.039e+07
2023-07-07 14:11:14,051 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8300, best=0.90, avg=0.89, std=0.00, steps=5.100e+07
2023-07-07 14:11:18,194 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8400, best=0.90, avg=0.89, std=0.00, steps=5.162e+07
2023-07-07 14:11:22,362 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8500, best=0.90, avg=0.89, std=0.00, steps=5.223e+07
2023-07-07 14:11:26,510 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8600, best=0.90, avg=0.89, std=0.00, steps=5.284e+07
2023-07-07 14:11:30,654 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8700, best=0.90, avg=0.89, std=0.00, steps=5.346e+07
2023-07-07 14:11:34,786 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8800, best=0.90, avg=0.89, std=0.00, steps=5.407e+07
2023-07-07 14:11:38,932 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8900, best=0.90, avg=0.89, std=0.00, steps=5.469e+07
2023-07-07 14:11:43,073 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9000, best=0.90, avg=0.89, std=0.00, steps=5.530e+07
2023-07-07 14:11:47,220 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9100, best=0.90, avg=0.89, std=0.00, steps=5.592e+07
2023-07-07 14:11:51,378 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9200, best=0.90, avg=0.89, std=0.00, steps=5.653e+07
2023-07-07 14:11:55,539 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9300, best=0.90, avg=0.89, std=0.00, steps=5.715e+07
2023-07-07 14:11:59,689 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9400, best=0.90, avg=0.89, std=0.00, steps=5.776e+07
2023-07-07 14:12:03,851 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9500, best=0.90, avg=0.89, std=0.00, steps=5.837e+07
2023-07-07 14:12:07,997 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9600, best=0.90, avg=0.89, std=0.00, steps=5.899e+07
2023-07-07 14:12:12,158 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9700, best=0.90, avg=0.89, std=0.00, steps=5.960e+07
2023-07-07 14:12:16,310 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9800, best=0.90, avg=0.89, std=0.00, steps=6.022e+07
2023-07-07 14:12:20,464 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9900, best=0.90, avg=0.89, std=0.00, steps=6.083e+07
2023-07-07 14:12:24,611 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10000, best=0.90, avg=0.89, std=0.00, steps=6.145e+07
2023-07-07 14:12:28,748 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10100, best=0.90, avg=0.89, std=0.00, steps=6.206e+07
2023-07-07 14:12:32,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10200, best=0.90, avg=0.89, std=0.00, steps=6.267e+07
2023-07-07 14:12:37,021 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10300, best=0.90, avg=0.89, std=0.00, steps=6.329e+07
2023-07-07 14:12:41,171 -        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 14:12:45,319 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10500, best=0.90, avg=0.89, std=0.00, steps=6.452e+07
2023-07-07 14:12:49,471 -        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 14:12:53,623 -        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 14:12:57,773 -        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 14:13:01,933 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10900, best=0.91, avg=0.89, std=0.00, steps=6.698e+07
2023-07-07 14:13:06,081 -        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 14:13:10,235 -        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 14:13:14,387 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11200, best=0.90, avg=0.90, std=0.00, steps=6.882e+07
2023-07-07 14:13:18,561 -        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 14:13:22,704 -        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 14:13:26,842 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11500, best=0.90, avg=0.90, std=0.00, steps=7.066e+07
2023-07-07 14:13:30,999 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11600, best=0.91, avg=0.90, std=0.00, steps=7.128e+07
2023-07-07 14:13:35,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11700, best=0.90, avg=0.90, std=0.00, steps=7.189e+07
2023-07-07 14:13:39,323 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11800, best=0.91, avg=0.90, std=0.00, steps=7.251e+07
2023-07-07 14:13:43,492 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11900, best=0.90, avg=0.90, std=0.00, steps=7.312e+07
2023-07-07 14:13:47,621 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11999, best=0.91, avg=0.90, std=0.00, steps=7.373e+07
2023-07-07 14:13:47,622 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 14:13:47,651 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:13:47,651 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:13:47,688 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:13:54,732 -        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 14:14:00,181 -        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 14:14:05,634 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 14:14:11,087 -        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 14:14:16,520 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 500, best=0.53, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 14:14:21,970 -        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 14:14:27,398 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 14:14:32,815 -        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 14:14:38,237 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 14:14:43,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 14:14:49,100 -        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 14:14:54,532 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1200, best=0.53, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 14:14:59,953 -        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 14:15:05,412 -        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 14:15:10,872 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:15:16,309 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1600, best=0.53, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 14:15:21,742 -        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 14:15:27,182 -        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 14:15:32,611 -        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 14:15:38,028 -        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 14:15:43,464 -        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 14:15:48,899 -        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 14:15:54,325 -        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 14:15:59,751 -        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 14:16:05,180 -        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 14:16:10,629 -        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 14:16:16,079 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 14:16:21,517 -        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 14:16:26,943 -        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 14:16:32,373 -        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 14:16:37,825 -        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 14:16:43,260 -        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 14:16:48,692 -        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 14:16:54,141 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3400, best=0.53, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 14:16:59,582 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3500, best=0.53, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 14:17:05,039 -        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 14:17:10,479 -        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 14:17:15,903 -        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 14:17:21,331 -        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 14:17:26,775 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4000, best=0.53, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:17:32,218 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4100, best=0.53, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 14:17:37,647 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 14:17:43,105 -        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 14:17:48,537 -        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 14:17:53,993 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:17:59,435 -        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 14:18:04,870 -        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 14:18:10,308 -        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 14:18:15,741 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4900, best=0.53, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 14:18:21,175 -        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 14:18:26,607 -        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 14:18:32,075 -        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 14:18:37,517 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=4.343e+07
2023-07-07 14:18:42,975 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 14:18:48,422 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=4.506e+07
2023-07-07 14:18:53,853 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 14:18:59,300 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 14:19:04,742 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 14:19:10,167 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 14:19:15,596 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6000, best=0.53, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:19:21,012 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=4.998e+07
2023-07-07 14:19:26,428 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6200, best=0.53, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 14:19:31,865 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:19:37,300 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 14:19:42,737 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6500, best=0.53, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 14:19:48,173 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6600, best=0.53, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 14:19:53,607 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 14:19:59,073 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 14:20:04,512 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 14:20:09,956 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 14:20:15,398 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 14:20:20,843 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 14:20:26,292 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.01, steps=5.981e+07
2023-07-07 14:20:31,726 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=6.063e+07
2023-07-07 14:20:37,191 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:20:42,630 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=6.227e+07
2023-07-07 14:20:48,053 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=6.309e+07
2023-07-07 14:20:53,487 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 14:20:58,935 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=6.472e+07
2023-07-07 14:21:04,383 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=6.554e+07
2023-07-07 14:21:09,849 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=6.636e+07
2023-07-07 14:21:15,315 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=6.718e+07
2023-07-07 14:21:20,736 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=6.800e+07
2023-07-07 14:21:26,173 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=6.882e+07
2023-07-07 14:21:31,621 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=6.964e+07
2023-07-07 14:21:37,063 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=7.046e+07
2023-07-07 14:21:42,493 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 14:21:47,938 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=7.210e+07
2023-07-07 14:21:53,377 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=7.292e+07
2023-07-07 14:21:58,807 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 14:22:04,235 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=7.456e+07
2023-07-07 14:22:09,690 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=7.537e+07
2023-07-07 14:22:15,144 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=7.619e+07
2023-07-07 14:22:20,602 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9400, best=0.53, avg=0.50, std=0.01, steps=7.701e+07
2023-07-07 14:22:26,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=7.783e+07
2023-07-07 14:22:31,490 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=7.865e+07
2023-07-07 14:22:36,929 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=7.947e+07
2023-07-07 14:22:42,379 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.01, steps=8.029e+07
2023-07-07 14:22:47,812 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 14:22:53,255 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=8.193e+07
2023-07-07 14:22:58,699 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=8.275e+07
2023-07-07 14:23:04,145 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 14:23:09,584 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=8.439e+07
2023-07-07 14:23:15,014 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10400, best=0.65, avg=0.64, std=0.00, steps=8.520e+07
2023-07-07 14:23:20,478 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10500, best=0.69, avg=0.67, std=0.01, steps=8.602e+07
2023-07-07 14:23:25,905 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10600, best=0.71, avg=0.70, std=0.01, steps=8.684e+07
2023-07-07 14:23:31,356 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10700, best=0.72, avg=0.71, std=0.01, steps=8.766e+07
2023-07-07 14:23:36,790 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10800, best=0.72, avg=0.71, std=0.01, steps=8.848e+07
2023-07-07 14:23:42,239 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10900, best=0.72, avg=0.71, std=0.00, steps=8.930e+07
2023-07-07 14:23:47,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11000, best=0.73, avg=0.72, std=0.01, steps=9.012e+07
2023-07-07 14:23:53,124 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11100, best=0.74, avg=0.72, std=0.01, steps=9.094e+07
2023-07-07 14:23:58,561 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11200, best=0.74, avg=0.73, std=0.01, steps=9.176e+07
2023-07-07 14:24:04,001 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11300, best=0.75, avg=0.73, std=0.00, steps=9.258e+07
2023-07-07 14:24:09,450 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11400, best=0.75, avg=0.74, std=0.01, steps=9.340e+07
2023-07-07 14:24:14,902 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11500, best=0.76, avg=0.74, std=0.01, steps=9.422e+07
2023-07-07 14:24:20,363 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11600, best=0.76, avg=0.75, std=0.01, steps=9.504e+07
2023-07-07 14:24:25,798 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11700, best=0.77, avg=0.75, std=0.01, steps=9.585e+07
2023-07-07 14:24:31,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11800, best=0.78, avg=0.76, std=0.01, steps=9.667e+07
2023-07-07 14:24:36,679 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11900, best=0.79, avg=0.77, std=0.01, steps=9.749e+07
2023-07-07 14:24:42,072 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11999, best=0.78, avg=0.77, std=0.01, steps=9.830e+07
2023-07-07 14:24:42,073 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 14:24:42,103 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:24:42,103 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:24:42,138 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:24:51,766 -        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 14:24:59,833 -        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 14:25:07,856 -        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 14:25:15,869 -        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 14:25:23,883 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 14:25:31,899 -        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 14:25:39,904 -        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 14:25:47,910 -        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 14:25:55,905 -        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 14:26:03,931 -        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 14:26:11,916 -        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 14:26:19,921 -        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 14:26:27,926 -        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 14:26:35,937 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 14:26:43,940 -        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 14:26:51,943 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 14:26:59,943 -        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 14:27:07,936 -        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 14:27:15,912 -        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 14:27:23,909 -        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 14:27:31,910 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 14:27:39,889 -        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 14:27:47,865 -        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 14:27:55,846 -        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 14:28:03,852 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 14:28:11,846 -        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 14:28:19,852 -        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 14:28:27,837 -        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 14:28:35,826 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 14:28:43,816 -        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 14:28:51,817 -        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 14:28:59,825 -        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 14:29:07,817 -        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 14:29:15,818 -        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 14:29:23,805 -        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 14:29:31,806 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3600, best=0.53, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 14:29:39,806 -        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 14:29:47,793 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 14:29:55,765 -        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 14:30:03,738 -        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 14:30:11,726 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 14:30:19,709 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:30:27,693 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4300, best=0.53, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 14:30:35,688 -        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 14:30:43,678 -        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 14:30:51,694 -        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 14:30:59,713 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 14:31:07,758 -        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 14:31:15,763 -        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 14:31:23,747 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:31:31,763 -        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 14:31:39,774 -        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 14:31:47,760 -        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 14:31:55,774 -        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 14:32:03,772 -        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 14:32:11,760 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5600, best=0.53, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 14:32:19,758 -        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 14:32:27,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 14:32:35,755 -        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 14:32:43,763 -        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 14:32:51,752 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=7.497e+07
2023-07-07 14:32:59,758 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 14:33:07,745 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 14:33:15,766 -        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 14:33:23,758 -        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 14:33:31,749 -        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 14:33:39,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6700, best=0.53, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 14:33:47,767 -        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 14:33:55,793 -        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 14:34:03,802 -        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 14:34:11,836 -        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 14:34:19,829 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 14:34:27,806 -        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 14:34:35,787 -        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 14:34:43,788 -        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 14:34:51,777 -        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 14:34:59,764 -        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 14:35:07,773 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 14:35:15,770 -        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 14:35:23,765 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8000, best=0.64, avg=0.63, std=0.00, steps=9.832e+07
2023-07-07 14:35:31,756 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8100, best=0.65, avg=0.64, std=0.01, steps=9.955e+07
2023-07-07 14:35:39,746 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8200, best=0.65, avg=0.64, std=0.01, steps=1.008e+08
2023-07-07 14:35:47,740 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8300, best=0.65, avg=0.64, std=0.01, steps=1.020e+08
2023-07-07 14:35:55,730 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8400, best=0.65, avg=0.64, std=0.00, steps=1.032e+08
2023-07-07 14:36:03,712 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8500, best=0.65, avg=0.64, std=0.00, steps=1.045e+08
2023-07-07 14:36:11,691 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8600, best=0.65, avg=0.64, std=0.01, steps=1.057e+08
2023-07-07 14:36:19,668 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8700, best=0.65, avg=0.64, std=0.01, steps=1.069e+08
2023-07-07 14:36:27,659 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8800, best=0.68, avg=0.66, std=0.01, steps=1.081e+08
2023-07-07 14:36:35,653 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8900, best=0.68, avg=0.67, std=0.01, steps=1.094e+08
2023-07-07 14:36:43,686 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9000, best=0.70, avg=0.68, std=0.01, steps=1.106e+08
2023-07-07 14:36:51,686 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9100, best=0.69, avg=0.68, std=0.01, steps=1.118e+08
2023-07-07 14:36:59,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9200, best=0.71, avg=0.70, std=0.01, steps=1.131e+08
2023-07-07 14:37:07,691 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9300, best=0.73, avg=0.71, std=0.01, steps=1.143e+08
2023-07-07 14:37:15,686 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9400, best=0.73, avg=0.72, std=0.01, steps=1.155e+08
2023-07-07 14:37:23,701 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9500, best=0.73, avg=0.72, std=0.01, steps=1.167e+08
2023-07-07 14:37:31,700 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9600, best=0.73, avg=0.72, std=0.00, steps=1.180e+08
2023-07-07 14:37:39,712 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9700, best=0.73, avg=0.72, std=0.01, steps=1.192e+08
2023-07-07 14:37:47,726 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9800, best=0.74, avg=0.72, std=0.01, steps=1.204e+08
2023-07-07 14:37:55,734 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9900, best=0.74, avg=0.72, std=0.01, steps=1.217e+08
2023-07-07 14:38:03,730 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10000, best=0.74, avg=0.73, std=0.01, steps=1.229e+08
2023-07-07 14:38:11,738 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10100, best=0.74, avg=0.73, std=0.01, steps=1.241e+08
2023-07-07 14:38:19,727 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10200, best=0.74, avg=0.73, std=0.01, steps=1.253e+08
2023-07-07 14:38:27,738 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10300, best=0.75, avg=0.73, std=0.01, steps=1.266e+08
2023-07-07 14:38:35,749 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10400, best=0.75, avg=0.74, std=0.01, steps=1.278e+08
2023-07-07 14:38:43,751 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10500, best=0.75, avg=0.73, std=0.01, steps=1.290e+08
2023-07-07 14:38:51,762 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10600, best=0.75, avg=0.74, std=0.00, steps=1.303e+08
2023-07-07 14:38:59,764 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10700, best=0.76, avg=0.74, std=0.01, steps=1.315e+08
2023-07-07 14:39:07,786 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10800, best=0.76, avg=0.74, std=0.01, steps=1.327e+08
2023-07-07 14:39:15,797 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10900, best=0.76, avg=0.75, std=0.01, steps=1.340e+08
2023-07-07 14:39:23,811 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11000, best=0.76, avg=0.75, std=0.01, steps=1.352e+08
2023-07-07 14:39:31,810 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11100, best=0.76, avg=0.75, std=0.01, steps=1.364e+08
2023-07-07 14:39:39,809 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11200, best=0.77, avg=0.75, std=0.01, steps=1.376e+08
2023-07-07 14:39:47,809 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11300, best=0.77, avg=0.75, std=0.01, steps=1.389e+08
2023-07-07 14:39:55,799 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11400, best=0.77, avg=0.75, std=0.01, steps=1.401e+08
2023-07-07 14:40:03,780 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11500, best=0.77, avg=0.75, std=0.01, steps=1.413e+08
2023-07-07 14:40:11,755 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11600, best=0.77, avg=0.76, std=0.01, steps=1.426e+08
2023-07-07 14:40:19,729 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11700, best=0.77, avg=0.76, std=0.01, steps=1.438e+08
2023-07-07 14:40:27,708 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11800, best=0.77, avg=0.76, std=0.01, steps=1.450e+08
2023-07-07 14:40:35,684 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11900, best=0.77, avg=0.76, std=0.01, steps=1.462e+08
2023-07-07 14:40:43,624 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11999, best=0.77, avg=0.76, std=0.01, steps=1.475e+08
2023-07-07 14:40:43,625 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 14:40:43,649 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:40:43,650 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:40:43,680 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:40:50,673 -        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 14:40:56,106 -        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 14:41:01,523 -        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 14:41:06,951 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 14:41:12,385 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=4.104e+06
2023-07-07 14:41:17,806 -        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 14:41:23,234 -        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 14:41:28,645 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=6.562e+06
2023-07-07 14:41:34,056 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 900, best=0.51, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 14:41:39,492 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 14:41:44,947 -        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 14:41:50,375 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 14:41:55,802 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.066e+07
2023-07-07 14:42:01,229 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 14:42:06,656 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:42:12,096 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 14:42:17,533 -        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 14:42:22,963 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=1.475e+07
2023-07-07 14:42:28,387 -        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 14:42:33,848 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 14:42:39,286 -        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 14:42:44,730 -        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 14:42:50,160 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 14:42:55,593 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 14:43:01,019 -        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 14:43:06,442 -        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 14:43:11,883 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.00, steps=2.213e+07
2023-07-07 14:43:17,323 -        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 14:43:22,750 -        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 14:43:28,182 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 14:43:33,602 -        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 14:43:39,079 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 14:43:44,543 -        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 14:43:49,977 -        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 14:43:55,414 -        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 14:44:00,847 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 14:44:06,288 -        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 14:44:11,732 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=3.114e+07
2023-07-07 14:44:17,169 -        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 14:44:22,610 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=3.278e+07
2023-07-07 14:44:28,045 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 14:44:33,489 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 14:44:38,924 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=3.523e+07
2023-07-07 14:44:44,371 -        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 14:44:49,814 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:44:55,243 -        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 14:45:00,683 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=3.851e+07
2023-07-07 14:45:06,110 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 14:45:11,558 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 14:45:16,986 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 14:45:22,426 -        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 14:45:27,866 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=4.261e+07
2023-07-07 14:45:33,317 -        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 14:45:38,753 -        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 14:45:44,197 -        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 14:45:49,622 -        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 14:45:55,038 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 14:46:00,467 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 14:46:05,893 -        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 14:46:11,336 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:46:16,776 -        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 14:46:22,210 -        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 14:46:27,653 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=5.162e+07
2023-07-07 14:46:33,086 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=5.244e+07
2023-07-07 14:46:38,528 -        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 14:46:43,973 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 14:46:49,407 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 14:46:54,825 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 14:47:00,255 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 14:47:05,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 14:47:11,124 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.01, steps=5.817e+07
2023-07-07 14:47:16,563 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 14:47:21,999 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=5.981e+07
2023-07-07 14:47:27,433 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=6.063e+07
2023-07-07 14:47:32,867 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:47:38,304 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=6.227e+07
2023-07-07 14:47:43,739 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=6.309e+07
2023-07-07 14:47:49,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 14:47:54,606 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=6.472e+07
2023-07-07 14:48:00,029 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=6.554e+07
2023-07-07 14:48:05,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.01, steps=6.636e+07
2023-07-07 14:48:10,890 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=6.718e+07
2023-07-07 14:48:16,315 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=6.800e+07
2023-07-07 14:48:21,747 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.01, steps=6.882e+07
2023-07-07 14:48:27,170 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.01, steps=6.964e+07
2023-07-07 14:48:32,596 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=7.046e+07
2023-07-07 14:48:38,021 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 14:48:43,450 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.01, steps=7.210e+07
2023-07-07 14:48:48,878 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.01, steps=7.292e+07
2023-07-07 14:48:54,312 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 14:48:59,742 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.00, steps=7.456e+07
2023-07-07 14:49:05,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.01, steps=7.537e+07
2023-07-07 14:49:10,610 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.01, steps=7.619e+07
2023-07-07 14:49:16,053 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.01, steps=7.701e+07
2023-07-07 14:49:21,485 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.01, steps=7.783e+07
2023-07-07 14:49:26,915 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=7.865e+07
2023-07-07 14:49:32,341 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=7.947e+07
2023-07-07 14:49:37,774 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=8.029e+07
2023-07-07 14:49:43,198 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=8.111e+07
2023-07-07 14:49:48,624 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=8.193e+07
2023-07-07 14:49:54,052 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.01, steps=8.275e+07
2023-07-07 14:49:59,486 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 14:50:04,921 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.01, steps=8.439e+07
2023-07-07 14:50:10,347 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=8.520e+07
2023-07-07 14:50:15,778 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.01, steps=8.602e+07
2023-07-07 14:50:21,215 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=8.684e+07
2023-07-07 14:50:26,655 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.01, steps=8.766e+07
2023-07-07 14:50:32,097 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.01, steps=8.848e+07
2023-07-07 14:50:37,537 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10900, best=0.52, avg=0.50, std=0.01, steps=8.930e+07
2023-07-07 14:50:42,970 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.01, steps=9.012e+07
2023-07-07 14:50:48,404 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 14:50:53,850 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.01, steps=9.176e+07
2023-07-07 14:50:59,282 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11300, best=0.52, avg=0.50, std=0.01, steps=9.258e+07
2023-07-07 14:51:04,706 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11400, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 14:51:10,143 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.01, steps=9.422e+07
2023-07-07 14:51:15,570 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11600, best=0.67, avg=0.66, std=0.00, steps=9.504e+07
2023-07-07 14:51:21,011 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11700, best=0.70, avg=0.69, std=0.00, steps=9.585e+07
2023-07-07 14:51:26,455 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11800, best=0.72, avg=0.71, std=0.00, steps=9.667e+07
2023-07-07 14:51:31,880 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11900, best=0.73, avg=0.72, std=0.00, steps=9.749e+07
2023-07-07 14:51:37,263 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11999, best=0.75, avg=0.73, std=0.00, steps=9.830e+07
2023-07-07 14:51:37,263 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 14:51:37,288 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:51:37,288 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:51:37,318 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:51:45,589 -        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 14:51:52,295 -        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 14:51:58,988 -        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 14:52:05,711 -        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 14:52:12,426 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=5.130e+06
2023-07-07 14:52:19,129 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=6.154e+06
2023-07-07 14:52:25,867 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=7.178e+06
2023-07-07 14:52:32,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=8.202e+06
2023-07-07 14:52:39,279 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 900, best=0.51, avg=0.50, std=0.01, steps=9.226e+06
2023-07-07 14:52:45,994 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=1.025e+07
2023-07-07 14:52:52,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.01, steps=1.127e+07
2023-07-07 14:52:59,394 -        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 14:53:06,093 -        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 14:53:12,782 -        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 14:53:19,487 -        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 14:53:26,188 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 14:53:32,899 -        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 14:53:39,604 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 14:53:46,321 -        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 14:53:53,015 -        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 14:53:59,722 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 14:54:06,454 -        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 14:54:13,175 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.01, steps=2.356e+07
2023-07-07 14:54:19,884 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 14:54:26,579 -        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 14:54:33,285 -        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 14:54:39,976 -        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 14:54:46,672 -        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 14:54:53,393 -        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 14:55:00,089 -        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 14:55:06,780 -        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 14:55:13,498 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:55:20,213 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 14:55:26,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=3.483e+07
2023-07-07 14:55:33,630 -        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 14:55:40,335 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:55:47,025 -        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 14:55:53,737 -        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 14:56:00,435 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=3.995e+07
2023-07-07 14:56:07,158 -        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 14:56:13,859 -        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 14:56:20,556 -        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 14:56:27,263 -        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 14:56:33,969 -        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 14:56:40,676 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=4.609e+07
2023-07-07 14:56:47,375 -        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 14:56:54,075 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=4.814e+07
2023-07-07 14:57:00,776 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:57:07,485 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.01, steps=5.019e+07
2023-07-07 14:57:14,191 -        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 14:57:20,885 -        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 14:57:27,591 -        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 14:57:34,276 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=5.428e+07
2023-07-07 14:57:40,977 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 14:57:47,677 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=5.633e+07
2023-07-07 14:57:54,393 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 14:58:01,108 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=5.838e+07
2023-07-07 14:58:07,818 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=5.940e+07
2023-07-07 14:58:14,535 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.00, steps=6.043e+07
2023-07-07 14:58:21,231 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:58:27,928 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.01, steps=6.247e+07
2023-07-07 14:58:34,630 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=6.350e+07
2023-07-07 14:58:41,348 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=6.452e+07
2023-07-07 14:58:48,048 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=6.555e+07
2023-07-07 14:58:54,740 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=6.657e+07
2023-07-07 14:59:01,445 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=6.759e+07
2023-07-07 14:59:08,140 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=6.862e+07
2023-07-07 14:59:14,839 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=6.964e+07
2023-07-07 14:59:21,553 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6900, best=0.66, avg=0.65, std=0.00, steps=7.067e+07
2023-07-07 14:59:28,256 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7000, best=0.69, avg=0.68, std=0.00, steps=7.169e+07
2023-07-07 14:59:34,957 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7100, best=0.70, avg=0.69, std=0.00, steps=7.271e+07
2023-07-07 14:59:41,637 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7200, best=0.71, avg=0.70, std=0.00, steps=7.374e+07
2023-07-07 14:59:48,329 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7300, best=0.72, avg=0.71, std=0.00, steps=7.476e+07
2023-07-07 14:59:55,057 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7400, best=0.73, avg=0.72, std=0.00, steps=7.579e+07
2023-07-07 15:00:01,753 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7500, best=0.73, avg=0.72, std=0.00, steps=7.681e+07
2023-07-07 15:00:08,459 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7600, best=0.74, avg=0.73, std=0.00, steps=7.783e+07
2023-07-07 15:00:15,151 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7700, best=0.74, avg=0.73, std=0.00, steps=7.886e+07
2023-07-07 15:00:21,856 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7800, best=0.75, avg=0.74, std=0.00, steps=7.988e+07
2023-07-07 15:00:28,558 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7900, best=0.75, avg=0.74, std=0.00, steps=8.091e+07
2023-07-07 15:00:35,258 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8000, best=0.76, avg=0.75, std=0.00, steps=8.193e+07
2023-07-07 15:00:41,953 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8100, best=0.76, avg=0.75, std=0.00, steps=8.295e+07
2023-07-07 15:00:48,670 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8200, best=0.77, avg=0.76, std=0.00, steps=8.398e+07
2023-07-07 15:00:55,376 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8300, best=0.78, avg=0.76, std=0.00, steps=8.500e+07
2023-07-07 15:01:02,107 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8400, best=0.78, avg=0.77, std=0.00, steps=8.603e+07
2023-07-07 15:01:08,811 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8500, best=0.78, avg=0.77, std=0.00, steps=8.705e+07
2023-07-07 15:01:15,524 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8600, best=0.78, avg=0.77, std=0.00, steps=8.807e+07
2023-07-07 15:01:22,232 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8700, best=0.79, avg=0.78, std=0.00, steps=8.910e+07
2023-07-07 15:01:28,941 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8800, best=0.79, avg=0.78, std=0.00, steps=9.012e+07
2023-07-07 15:01:35,637 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8900, best=0.79, avg=0.78, std=0.00, steps=9.115e+07
2023-07-07 15:01:42,333 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9000, best=0.79, avg=0.78, std=0.00, steps=9.217e+07
2023-07-07 15:01:49,038 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9100, best=0.80, avg=0.79, std=0.00, steps=9.319e+07
2023-07-07 15:01:55,733 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9200, best=0.80, avg=0.79, std=0.00, steps=9.422e+07
2023-07-07 15:02:02,429 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9300, best=0.80, avg=0.79, std=0.00, steps=9.524e+07
2023-07-07 15:02:09,131 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9400, best=0.80, avg=0.79, std=0.00, steps=9.627e+07
2023-07-07 15:02:15,834 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9500, best=0.80, avg=0.80, std=0.00, steps=9.729e+07
2023-07-07 15:02:22,539 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9600, best=0.81, avg=0.80, std=0.00, steps=9.831e+07
2023-07-07 15:02:29,253 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9700, best=0.81, avg=0.80, std=0.00, steps=9.934e+07
2023-07-07 15:02:35,957 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9800, best=0.81, avg=0.80, std=0.00, steps=1.004e+08
2023-07-07 15:02:42,673 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9900, best=0.81, avg=0.80, std=0.00, steps=1.014e+08
2023-07-07 15:02:49,370 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10000, best=0.81, avg=0.81, std=0.00, steps=1.024e+08
2023-07-07 15:02:56,062 -        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 15:03:02,766 -        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 15:03:09,465 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10300, best=0.82, avg=0.81, std=0.00, steps=1.055e+08
2023-07-07 15:03:16,168 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10400, best=0.82, avg=0.81, std=0.00, steps=1.065e+08
2023-07-07 15:03:22,863 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10500, best=0.82, avg=0.81, std=0.00, steps=1.075e+08
2023-07-07 15:03:29,575 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10600, best=0.82, avg=0.81, std=0.00, steps=1.086e+08
2023-07-07 15:03:36,283 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10700, best=0.82, avg=0.81, std=0.00, steps=1.096e+08
2023-07-07 15:03:42,984 -        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 15:03:49,684 -        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 15:03:56,403 -        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 15:04:03,103 -        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 15:04:09,806 -        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 15:04:16,506 -        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 15:04:23,209 -        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 15:04:29,899 -        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 15:04:36,624 -        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 15:04:43,323 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11700, best=0.84, avg=0.83, std=0.00, steps=1.198e+08
2023-07-07 15:04:50,026 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11800, best=0.84, avg=0.83, std=0.00, steps=1.208e+08
2023-07-07 15:04:56,736 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11900, best=0.83, avg=0.83, std=0.00, steps=1.219e+08
2023-07-07 15:05:03,381 -        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 15:05:03,382 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 15:05:03,407 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:05:03,407 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:05:03,437 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:05:12,973 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 15:05:20,949 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 15:05:28,920 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 300, best=0.51, avg=0.50, std=0.01, steps=3.699e+06
2023-07-07 15:05:36,894 -        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 15:05:44,851 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=6.156e+06
2023-07-07 15:05:52,828 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 600, best=0.51, avg=0.50, std=0.00, steps=7.385e+06
2023-07-07 15:06:00,807 -        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 15:06:08,784 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 15:06:16,778 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 900, best=0.51, avg=0.50, std=0.01, steps=1.107e+07
2023-07-07 15:06:24,739 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 15:06:32,711 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.01, steps=1.353e+07
2023-07-07 15:06:40,672 -        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 15:06:48,667 -        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 15:06:56,636 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.01, steps=1.722e+07
2023-07-07 15:07:04,624 -        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 15:07:12,607 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 15:07:20,592 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 15:07:28,574 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 15:07:36,549 -        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 15:07:44,529 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.00, steps=2.459e+07
2023-07-07 15:07:52,501 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 15:08:00,471 -        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 15:08:08,442 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.00, steps=2.827e+07
2023-07-07 15:08:16,431 -        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 15:08:24,439 -        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 15:08:32,431 -        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 15:08:40,403 -        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 15:08:48,393 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.00, steps=3.442e+07
2023-07-07 15:08:56,373 -        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 15:09:04,347 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=3.688e+07
2023-07-07 15:09:12,330 -        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 15:09:20,303 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 15:09:28,277 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=4.056e+07
2023-07-07 15:09:36,257 -        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 15:09:44,270 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 15:09:52,257 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3600, best=0.51, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 15:10:00,256 -        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 15:10:08,252 -        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 15:10:16,240 -        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 15:10:24,212 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.00, steps=4.916e+07
2023-07-07 15:10:32,197 -        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 15:10:40,186 -        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 15:10:48,167 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=5.285e+07
2023-07-07 15:10:56,150 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 15:11:04,144 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 15:11:12,135 -        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 15:11:20,129 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=5.777e+07
2023-07-07 15:11:28,106 -        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 15:11:36,078 -        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 15:11:44,065 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=6.145e+07
2023-07-07 15:11:52,049 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.01, steps=6.268e+07
2023-07-07 15:12:00,053 -        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 15:12:08,048 -        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 15:12:16,025 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=6.637e+07
2023-07-07 15:12:23,998 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.01, steps=6.760e+07
2023-07-07 15:12:31,982 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 15:12:40,008 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 15:12:47,972 -        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 15:12:55,943 -        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 15:13:03,902 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 15:13:11,875 -        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 15:13:19,848 -        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 15:13:27,820 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 15:13:35,807 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 15:13:43,796 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 15:13:51,775 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 15:13:59,747 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 15:14:07,718 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 15:14:15,694 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=8.480e+07
2023-07-07 15:14:23,680 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=8.603e+07
2023-07-07 15:14:31,663 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 15:14:39,640 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=8.849e+07
2023-07-07 15:14:47,611 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.01, steps=8.971e+07
2023-07-07 15:14:55,587 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 15:15:03,554 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 15:15:11,524 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 15:15:19,508 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=9.463e+07
2023-07-07 15:15:27,503 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=9.586e+07
2023-07-07 15:15:35,505 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 15:15:43,499 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 15:15:51,494 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 15:15:59,492 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 15:16:07,476 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 15:16:15,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 15:16:23,427 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 15:16:31,409 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=1.057e+08
2023-07-07 15:16:39,383 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.01, steps=1.069e+08
2023-07-07 15:16:47,369 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 15:16:55,359 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.01, steps=1.094e+08
2023-07-07 15:17:03,336 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9000, best=0.61, avg=0.60, std=0.00, steps=1.106e+08
2023-07-07 15:17:11,328 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9100, best=0.65, avg=0.64, std=0.00, steps=1.118e+08
2023-07-07 15:17:19,300 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9200, best=0.66, avg=0.64, std=0.00, steps=1.131e+08
2023-07-07 15:17:27,284 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9300, best=0.66, avg=0.65, std=0.00, steps=1.143e+08
2023-07-07 15:17:35,271 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9400, best=0.67, avg=0.66, std=0.00, steps=1.155e+08
2023-07-07 15:17:43,234 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9500, best=0.68, avg=0.67, std=0.00, steps=1.167e+08
2023-07-07 15:17:51,219 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9600, best=0.69, avg=0.67, std=0.00, steps=1.180e+08
2023-07-07 15:17:59,193 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9700, best=0.70, avg=0.68, std=0.00, steps=1.192e+08
2023-07-07 15:18:07,157 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9800, best=0.70, avg=0.69, std=0.00, steps=1.204e+08
2023-07-07 15:18:15,137 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9900, best=0.70, avg=0.69, std=0.00, steps=1.217e+08
2023-07-07 15:18:23,107 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10000, best=0.70, avg=0.69, std=0.00, steps=1.229e+08
2023-07-07 15:18:31,089 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10100, best=0.71, avg=0.70, std=0.00, steps=1.241e+08
2023-07-07 15:18:39,060 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10200, best=0.71, avg=0.70, std=0.00, steps=1.253e+08
2023-07-07 15:18:47,036 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10300, best=0.71, avg=0.70, std=0.00, steps=1.266e+08
2023-07-07 15:18:55,006 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10400, best=0.72, avg=0.71, std=0.00, steps=1.278e+08
2023-07-07 15:19:02,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10500, best=0.72, avg=0.71, std=0.00, steps=1.290e+08
2023-07-07 15:19:10,977 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10600, best=0.72, avg=0.71, std=0.00, steps=1.303e+08
2023-07-07 15:19:18,961 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10700, best=0.72, avg=0.71, std=0.00, steps=1.315e+08
2023-07-07 15:19:26,944 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10800, best=0.72, avg=0.71, std=0.00, steps=1.327e+08
2023-07-07 15:19:34,933 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10900, best=0.73, avg=0.72, std=0.00, steps=1.340e+08
2023-07-07 15:19:42,916 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11000, best=0.73, avg=0.72, std=0.00, steps=1.352e+08
2023-07-07 15:19:50,902 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11100, best=0.73, avg=0.72, std=0.00, steps=1.364e+08
2023-07-07 15:19:58,876 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11200, best=0.73, avg=0.72, std=0.00, steps=1.376e+08
2023-07-07 15:20:06,874 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11300, best=0.73, avg=0.73, std=0.00, steps=1.389e+08
2023-07-07 15:20:14,871 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11400, best=0.74, avg=0.73, std=0.00, steps=1.401e+08
2023-07-07 15:20:22,858 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11500, best=0.74, avg=0.73, std=0.00, steps=1.413e+08
2023-07-07 15:20:30,821 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11600, best=0.74, avg=0.73, std=0.00, steps=1.426e+08
2023-07-07 15:20:38,785 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11700, best=0.74, avg=0.73, std=0.00, steps=1.438e+08
2023-07-07 15:20:46,760 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11800, best=0.74, avg=0.73, std=0.00, steps=1.450e+08
2023-07-07 15:20:54,741 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11900, best=0.75, avg=0.74, std=0.00, steps=1.462e+08
2023-07-07 15:21:02,663 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11999, best=0.75, avg=0.74, std=0.00, steps=1.475e+08
2023-07-07 15:21:02,663 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 15:21:02,689 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:21:02,689 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:21:02,724 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:21:14,931 -        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 15:21:25,502 -        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 15:21:36,070 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=4.932e+06
2023-07-07 15:21:46,633 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 400, best=0.51, avg=0.50, std=0.00, steps=6.570e+06
2023-07-07 15:21:57,232 -        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 15:22:07,814 -        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 15:22:18,422 -        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 15:22:28,989 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 15:22:39,556 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 15:22:50,160 -        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 15:23:00,758 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1100, best=0.51, avg=0.50, std=0.01, steps=1.804e+07
2023-07-07 15:23:11,345 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.968e+07
2023-07-07 15:23:21,916 -        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 15:23:32,491 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1400, best=0.51, avg=0.50, std=0.00, steps=2.295e+07
2023-07-07 15:23:43,059 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 15:23:53,634 -        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 15:24:04,226 -        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 15:24:14,805 -        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 15:24:25,391 -        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 15:24:35,999 -        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 15:24:46,567 -        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 15:24:57,135 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=3.606e+07
2023-07-07 15:25:07,709 -        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 15:25:18,285 -        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 15:25:28,857 -        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 15:25:39,438 -        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 15:25:50,012 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 15:26:00,587 -        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 15:26:11,164 -        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 15:26:21,748 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.01, steps=4.917e+07
2023-07-07 15:26:32,312 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=5.081e+07
2023-07-07 15:26:42,899 -        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 15:26:53,484 -        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 15:27:04,076 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=5.572e+07
2023-07-07 15:27:14,650 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=5.736e+07
2023-07-07 15:27:25,232 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=5.900e+07
2023-07-07 15:27:35,823 -        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 15:27:46,400 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=6.228e+07
2023-07-07 15:27:56,992 -        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 15:28:07,572 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.01, steps=6.555e+07
2023-07-07 15:28:18,173 -        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 15:28:28,793 -        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 15:28:39,404 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=7.047e+07
2023-07-07 15:28:49,989 -        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 15:29:00,557 -        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 15:29:11,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.01, steps=7.538e+07
2023-07-07 15:29:21,724 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.01, steps=7.702e+07
2023-07-07 15:29:32,318 -        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 15:29:42,899 -        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 15:29:53,483 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=8.194e+07
2023-07-07 15:30:04,066 -        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 15:30:14,671 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.01, steps=8.521e+07
2023-07-07 15:30:25,272 -        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 15:30:35,839 -        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 15:30:46,433 -        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 15:30:57,019 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=9.177e+07
2023-07-07 15:31:07,603 -        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 15:31:18,195 -        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 15:31:28,786 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=9.668e+07
2023-07-07 15:31:39,362 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 15:31:49,922 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=9.996e+07
2023-07-07 15:32:00,505 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.01, steps=1.016e+08
2023-07-07 15:32:11,099 -        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 15:32:21,664 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 15:32:32,241 -        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 15:32:42,839 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=1.082e+08
2023-07-07 15:32:53,416 -        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 15:33:04,003 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=1.114e+08
2023-07-07 15:33:14,608 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 15:33:25,209 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=1.147e+08
2023-07-07 15:33:35,809 -        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 15:33:46,378 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 15:33:56,933 -        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 15:34:07,502 -        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 15:34:18,091 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 15:34:28,659 -        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 15:34:39,250 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=1.262e+08
2023-07-07 15:34:49,815 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 15:35:00,386 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=1.294e+08
2023-07-07 15:35:10,974 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=1.311e+08
2023-07-07 15:35:21,553 -        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 15:35:32,152 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.01, steps=1.344e+08
2023-07-07 15:35:42,750 -        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 15:35:53,342 -        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 15:36:03,922 -        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 15:36:14,524 -        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 15:36:25,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.426e+08
2023-07-07 15:36:35,655 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.442e+08
2023-07-07 15:36:46,244 -        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 15:36:56,848 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 15:37:07,413 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=1.491e+08
2023-07-07 15:37:17,979 -        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 15:37:28,547 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=1.524e+08
2023-07-07 15:37:39,098 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=1.540e+08
2023-07-07 15:37:49,666 -        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 15:38:00,242 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.01, steps=1.573e+08
2023-07-07 15:38:10,824 -        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 15:38:21,395 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.01, steps=1.606e+08
2023-07-07 15:38:31,963 -        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 15:38:42,543 -        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 15:38:53,131 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.01, steps=1.655e+08
2023-07-07 15:39:03,705 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.671e+08
2023-07-07 15:39:14,294 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.01, steps=1.688e+08
2023-07-07 15:39:24,872 -        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 15:39:35,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=1.720e+08
2023-07-07 15:39:46,025 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=1.737e+08
2023-07-07 15:39:56,620 -        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 15:40:07,200 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10800, best=0.52, avg=0.50, std=0.01, steps=1.770e+08
2023-07-07 15:40:17,775 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=1.786e+08
2023-07-07 15:40:28,346 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11000, best=0.52, avg=0.50, std=0.01, steps=1.802e+08
2023-07-07 15:40:38,965 -        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 15:40:49,563 -        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 15:41:00,146 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=1.852e+08
2023-07-07 15:41:10,737 -        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 15:41:21,330 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.01, steps=1.884e+08
2023-07-07 15:41:31,928 -        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 15:41:42,536 -        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 15:41:53,128 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=1.933e+08
2023-07-07 15:42:03,688 -        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 15:42:14,150 -        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 15:42:14,151 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 15:42:14,175 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:42:14,175 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:42:14,205 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:42:26,570 -        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 15:42:37,139 -        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 15:42:47,682 -        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 15:42:58,215 -        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 15:43:08,766 -        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 15:43:19,292 -        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 15:43:29,847 -        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 15:43:40,398 -        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 15:43:50,924 -        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 15:44:01,459 -        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 15:44:12,023 -        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 15:44:22,568 -        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 15:44:33,145 -        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 15:44:43,710 -        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 15:44:54,253 -        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 15:45:04,812 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 15:45:15,355 -        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 15:45:25,901 -        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 15:45:36,446 -        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 15:45:46,983 -        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 15:45:57,528 -        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 15:46:08,071 -        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 15:46:18,634 -        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 15:46:29,184 -        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 15:46:39,714 -        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 15:46:50,266 -        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 15:47:00,823 -        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 15:47:11,358 -        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 15:47:21,901 -        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 15:47:32,428 -        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 15:47:42,962 -        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 15:47:53,517 -        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 15:48:04,047 -        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 15:48:14,567 -        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 15:48:25,107 -        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 15:48:35,636 -        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 15:48:46,196 -        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 15:48:56,766 -        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 15:49:07,310 -        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 15:49:17,828 -        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 15:49:28,377 -        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 15:49:38,949 -        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 15:49:49,488 -        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 15:50:00,032 -        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 15:50:10,573 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4500, best=0.51, avg=0.50, std=0.00, steps=7.374e+07
2023-07-07 15:50:21,117 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=7.538e+07
2023-07-07 15:50:31,667 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=7.702e+07
2023-07-07 15:50:42,219 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=7.866e+07
2023-07-07 15:50:52,756 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4900, best=0.51, avg=0.50, std=0.00, steps=8.030e+07
2023-07-07 15:51:03,287 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.00, steps=8.194e+07
2023-07-07 15:51:13,835 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=8.357e+07
2023-07-07 15:51:24,407 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5200, best=0.51, avg=0.50, std=0.00, steps=8.521e+07
2023-07-07 15:51:34,928 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=8.685e+07
2023-07-07 15:51:45,454 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 15:51:55,994 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 15:52:06,553 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=9.177e+07
2023-07-07 15:52:17,127 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=9.341e+07
2023-07-07 15:52:27,668 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=9.504e+07
2023-07-07 15:52:38,236 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=9.668e+07
2023-07-07 15:52:48,801 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=9.832e+07
2023-07-07 15:52:59,352 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=9.996e+07
2023-07-07 15:53:09,898 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 15:53:20,455 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.032e+08
2023-07-07 15:53:31,008 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.049e+08
2023-07-07 15:53:41,559 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.065e+08
2023-07-07 15:53:52,122 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.082e+08
2023-07-07 15:54:02,664 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.098e+08
2023-07-07 15:54:13,229 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.114e+08
2023-07-07 15:54:23,771 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.131e+08
2023-07-07 15:54:34,311 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7000, best=0.59, avg=0.58, std=0.00, steps=1.147e+08
2023-07-07 15:54:44,869 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7100, best=0.62, avg=0.61, std=0.00, steps=1.163e+08
2023-07-07 15:54:55,449 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7200, best=0.63, avg=0.63, std=0.00, steps=1.180e+08
2023-07-07 15:55:05,996 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7300, best=0.64, avg=0.64, std=0.00, steps=1.196e+08
2023-07-07 15:55:16,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7400, best=0.65, avg=0.64, std=0.00, steps=1.213e+08
2023-07-07 15:55:27,081 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7500, best=0.66, avg=0.65, std=0.00, steps=1.229e+08
2023-07-07 15:55:37,638 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7600, best=0.66, avg=0.66, std=0.00, steps=1.245e+08
2023-07-07 15:55:48,177 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7700, best=0.67, avg=0.66, std=0.00, steps=1.262e+08
2023-07-07 15:55:58,721 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7800, best=0.67, avg=0.66, std=0.00, steps=1.278e+08
2023-07-07 15:56:09,258 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7900, best=0.67, avg=0.67, std=0.00, steps=1.294e+08
2023-07-07 15:56:19,813 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8000, best=0.68, avg=0.67, std=0.00, steps=1.311e+08
2023-07-07 15:56:30,350 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8100, best=0.68, avg=0.67, std=0.00, steps=1.327e+08
2023-07-07 15:56:40,908 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8200, best=0.68, avg=0.68, std=0.00, steps=1.344e+08
2023-07-07 15:56:51,461 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8300, best=0.69, avg=0.68, std=0.00, steps=1.360e+08
2023-07-07 15:57:02,001 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8400, best=0.69, avg=0.68, std=0.00, steps=1.376e+08
2023-07-07 15:57:12,533 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8500, best=0.69, avg=0.68, std=0.00, steps=1.393e+08
2023-07-07 15:57:23,080 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8600, best=0.70, avg=0.69, std=0.00, steps=1.409e+08
2023-07-07 15:57:33,616 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8700, best=0.70, avg=0.69, std=0.00, steps=1.426e+08
2023-07-07 15:57:44,159 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8800, best=0.70, avg=0.69, std=0.00, steps=1.442e+08
2023-07-07 15:57:54,694 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8900, best=0.70, avg=0.69, std=0.00, steps=1.458e+08
2023-07-07 15:58:05,255 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9000, best=0.70, avg=0.70, std=0.00, steps=1.475e+08
2023-07-07 15:58:15,793 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9100, best=0.71, avg=0.70, std=0.00, steps=1.491e+08
2023-07-07 15:58:26,343 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9200, best=0.71, avg=0.70, std=0.00, steps=1.507e+08
2023-07-07 15:58:36,885 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9300, best=0.71, avg=0.70, std=0.00, steps=1.524e+08
2023-07-07 15:58:47,424 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9400, best=0.71, avg=0.71, std=0.00, steps=1.540e+08
2023-07-07 15:58:57,958 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9500, best=0.72, avg=0.71, std=0.00, steps=1.557e+08
2023-07-07 15:59:08,507 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9600, best=0.72, avg=0.71, std=0.00, steps=1.573e+08
2023-07-07 15:59:19,047 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9700, best=0.72, avg=0.71, std=0.00, steps=1.589e+08
2023-07-07 15:59:29,583 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9800, best=0.72, avg=0.71, std=0.00, steps=1.606e+08
2023-07-07 15:59:40,138 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9900, best=0.72, avg=0.72, std=0.00, steps=1.622e+08
2023-07-07 15:59:50,685 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10000, best=0.73, avg=0.72, std=0.00, steps=1.639e+08
2023-07-07 16:00:01,227 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10100, best=0.73, avg=0.72, std=0.00, steps=1.655e+08
2023-07-07 16:00:11,777 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10200, best=0.73, avg=0.72, std=0.00, steps=1.671e+08
2023-07-07 16:00:22,315 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10300, best=0.73, avg=0.72, std=0.00, steps=1.688e+08
2023-07-07 16:00:32,855 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10400, best=0.73, avg=0.72, std=0.00, steps=1.704e+08
2023-07-07 16:00:43,406 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10500, best=0.73, avg=0.73, std=0.00, steps=1.720e+08
2023-07-07 16:00:53,947 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10600, best=0.73, avg=0.73, std=0.00, steps=1.737e+08
2023-07-07 16:01:04,476 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10700, best=0.74, avg=0.73, std=0.00, steps=1.753e+08
2023-07-07 16:01:15,007 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10800, best=0.74, avg=0.73, std=0.00, steps=1.770e+08
2023-07-07 16:01:25,530 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10900, best=0.74, avg=0.73, std=0.00, steps=1.786e+08
2023-07-07 16:01:36,063 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11000, best=0.74, avg=0.73, std=0.00, steps=1.802e+08
2023-07-07 16:01:46,596 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11100, best=0.74, avg=0.73, std=0.00, steps=1.819e+08
2023-07-07 16:01:57,135 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11200, best=0.74, avg=0.73, std=0.00, steps=1.835e+08
2023-07-07 16:02:07,675 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11300, best=0.74, avg=0.73, std=0.00, steps=1.852e+08
2023-07-07 16:02:18,212 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11400, best=0.75, avg=0.74, std=0.00, steps=1.868e+08
2023-07-07 16:02:28,758 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11500, best=0.75, avg=0.74, std=0.00, steps=1.884e+08
2023-07-07 16:02:39,305 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11600, best=0.75, avg=0.74, std=0.00, steps=1.901e+08
2023-07-07 16:02:49,843 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11700, best=0.74, avg=0.74, std=0.00, steps=1.917e+08
2023-07-07 16:03:00,402 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11800, best=0.75, avg=0.74, std=0.00, steps=1.933e+08
2023-07-07 16:03:10,945 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11900, best=0.75, avg=0.74, std=0.00, steps=1.950e+08
2023-07-07 16:03:21,377 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11999, best=0.75, avg=0.74, std=0.00, steps=1.966e+08
2023-07-07 16:03:21,378 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 16:03:21,403 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:03:21,403 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:03:21,435 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:03:34,944 -        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 16:03:46,819 -        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 16:03:58,689 -        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 16:04:10,552 -        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 16:04:22,411 -        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 16:04:34,281 -        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 16:04:46,136 -        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 16:04:57,987 -        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 16:05:09,853 -        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 16:05:21,709 -        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 16:05:33,568 -        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 16:05:45,422 -        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 16:05:57,292 -        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 16:06:09,153 -        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 16:06:21,014 -        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 16:06:32,867 -        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 16:06:44,715 -        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 16:06:56,571 -        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 16:07:08,446 -        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 16:07:20,316 -        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 16:07:32,174 -        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 16:07:44,060 -        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 16:07:55,926 -        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 16:08:07,765 -        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 16:08:19,611 -        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 16:08:31,455 -        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 16:08:43,308 -        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 16:08:55,164 -        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 16:09:07,035 -        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 16:09:18,903 -        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 16:09:30,765 -        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 16:09:42,628 -        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 16:09:54,485 -        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 16:10:06,335 -        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 16:10:18,196 -        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 16:10:30,057 -        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 16:10:41,914 -        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 16:10:53,785 -        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 16:11:05,640 -        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 16:11:17,483 -        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 16:11:29,331 -        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 16:11:41,201 -        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 16:11:53,068 -        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 16:12:04,950 -        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 16:12:16,872 -        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 16:12:28,729 -        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 16:12:40,591 -        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 16:12:52,470 -        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 16:13:04,342 -        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 16:13:16,216 -        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 16:13:28,074 -        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 16:13:39,941 -        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 16:13:51,784 -        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 16:14:03,662 -        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 16:14:15,528 -        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 16:14:27,383 -        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 16:14:39,237 -        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 16:14:51,102 -        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 16:15:02,961 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.088e+08
2023-07-07 16:15:14,818 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 16:15:26,679 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.125e+08
2023-07-07 16:15:38,581 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.143e+08
2023-07-07 16:15:50,442 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.161e+08
2023-07-07 16:16:02,291 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.180e+08
2023-07-07 16:16:14,144 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.198e+08
2023-07-07 16:16:26,001 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 16:16:37,856 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.235e+08
2023-07-07 16:16:49,714 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.254e+08
2023-07-07 16:17:01,583 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.272e+08
2023-07-07 16:17:13,441 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 16:17:25,295 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.309e+08
2023-07-07 16:17:37,151 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.327e+08
2023-07-07 16:17:49,007 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.346e+08
2023-07-07 16:18:00,900 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.364e+08
2023-07-07 16:18:12,761 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.383e+08
2023-07-07 16:18:24,610 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.401e+08
2023-07-07 16:18:36,465 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.419e+08
2023-07-07 16:18:48,350 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.438e+08
2023-07-07 16:19:00,207 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.456e+08
2023-07-07 16:19:12,061 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 16:19:23,914 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.493e+08
2023-07-07 16:19:35,773 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.512e+08
2023-07-07 16:19:47,635 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.530e+08
2023-07-07 16:19:59,512 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.548e+08
2023-07-07 16:20:11,374 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.567e+08
2023-07-07 16:20:23,245 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.585e+08
2023-07-07 16:20:35,094 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.604e+08
2023-07-07 16:20:46,959 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8800, best=0.59, avg=0.59, std=0.00, steps=1.622e+08
2023-07-07 16:20:58,814 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8900, best=0.61, avg=0.60, std=0.00, steps=1.641e+08
2023-07-07 16:21:10,706 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9000, best=0.62, avg=0.62, std=0.00, steps=1.659e+08
2023-07-07 16:21:22,571 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9100, best=0.63, avg=0.62, std=0.00, steps=1.677e+08
2023-07-07 16:21:34,431 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9200, best=0.64, avg=0.63, std=0.00, steps=1.696e+08
2023-07-07 16:21:46,322 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9300, best=0.64, avg=0.64, std=0.00, steps=1.714e+08
2023-07-07 16:21:58,191 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9400, best=0.65, avg=0.64, std=0.00, steps=1.733e+08
2023-07-07 16:22:10,060 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9500, best=0.66, avg=0.65, std=0.00, steps=1.751e+08
2023-07-07 16:22:21,921 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9600, best=0.66, avg=0.65, std=0.00, steps=1.770e+08
2023-07-07 16:22:33,793 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9700, best=0.66, avg=0.65, std=0.00, steps=1.788e+08
2023-07-07 16:22:45,751 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9800, best=0.66, avg=0.66, std=0.00, steps=1.807e+08
2023-07-07 16:22:57,621 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9900, best=0.66, avg=0.66, std=0.00, steps=1.825e+08
2023-07-07 16:23:09,501 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10000, best=0.67, avg=0.66, std=0.00, steps=1.843e+08
2023-07-07 16:23:21,382 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10100, best=0.67, avg=0.66, std=0.00, steps=1.862e+08
2023-07-07 16:23:33,246 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10200, best=0.67, avg=0.67, std=0.00, steps=1.880e+08
2023-07-07 16:23:45,137 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10300, best=0.68, avg=0.67, std=0.00, steps=1.899e+08
2023-07-07 16:23:57,119 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10400, best=0.68, avg=0.67, std=0.00, steps=1.917e+08
2023-07-07 16:24:09,017 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10500, best=0.68, avg=0.67, std=0.00, steps=1.936e+08
2023-07-07 16:24:20,909 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10600, best=0.68, avg=0.67, std=0.00, steps=1.954e+08
2023-07-07 16:24:32,771 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10700, best=0.68, avg=0.67, std=0.00, steps=1.972e+08
2023-07-07 16:24:44,625 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10800, best=0.69, avg=0.68, std=0.00, steps=1.991e+08
2023-07-07 16:24:56,583 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10900, best=0.68, avg=0.68, std=0.00, steps=2.009e+08
2023-07-07 16:25:08,450 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11000, best=0.69, avg=0.68, std=0.00, steps=2.028e+08
2023-07-07 16:25:20,339 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11100, best=0.69, avg=0.68, std=0.00, steps=2.046e+08
2023-07-07 16:25:32,218 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11200, best=0.69, avg=0.68, std=0.00, steps=2.065e+08
2023-07-07 16:25:44,179 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11300, best=0.69, avg=0.68, std=0.00, steps=2.083e+08
2023-07-07 16:25:56,081 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11400, best=0.69, avg=0.68, std=0.00, steps=2.101e+08
2023-07-07 16:26:07,948 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11500, best=0.69, avg=0.69, std=0.00, steps=2.120e+08
2023-07-07 16:26:19,833 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11600, best=0.69, avg=0.69, std=0.00, steps=2.138e+08
2023-07-07 16:26:31,690 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11700, best=0.69, avg=0.69, std=0.00, steps=2.157e+08
2023-07-07 16:26:43,597 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11800, best=0.70, avg=0.69, std=0.00, steps=2.175e+08
2023-07-07 16:26:55,542 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11900, best=0.70, avg=0.69, std=0.00, steps=2.194e+08
2023-07-07 16:27:07,304 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11999, best=0.70, avg=0.69, std=0.00, steps=2.212e+08
2023-07-07 16:27:07,304 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 16:27:07,329 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:27:07,329 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:27:07,362 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:27:22,157 -        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 16:27:35,322 -        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 16:27:48,464 -        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 16:28:01,610 -        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 16:28:14,747 -        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 16:28:27,886 -        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 16:28:41,021 -        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 16:28:54,179 -        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 16:29:07,357 -        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 16:29:20,514 -        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 16:29:33,691 -        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 16:29:46,850 -        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 16:29:59,995 -        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 16:30:13,160 -        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 16:30:26,330 -        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 16:30:39,509 -        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 16:30:52,688 -        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 16:31:05,830 -        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 16:31:18,985 -        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 16:31:32,144 -        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 16:31:45,298 -        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 16:31:58,433 -        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 16:32:11,597 -        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 16:32:24,771 -        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 16:32:37,960 -        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 16:32:51,136 -        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 16:33:04,302 -        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 16:33:17,435 -        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 16:33:30,592 -        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 16:33:43,768 -        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 16:33:56,971 -        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 16:34:10,101 -        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 16:34:23,237 -        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 16:34:36,373 -        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 16:34:49,506 -        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 16:35:02,648 -        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 16:35:15,793 -        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 16:35:28,964 -        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 16:35:42,114 -        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 16:35:55,318 -        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 16:36:08,500 -        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 16:36:21,650 -        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 16:36:34,827 -        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 16:36:47,992 -        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 16:37:01,164 -        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 16:37:14,316 -        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 16:37:27,563 -        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 16:37:40,725 -        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 16:37:53,866 -        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 16:38:07,020 -        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 16:38:20,156 -        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 16:38:33,298 -        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 16:38:46,418 -        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 16:38:59,622 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 16:39:12,879 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=1.127e+08
2023-07-07 16:39:26,046 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.00, steps=1.147e+08
2023-07-07 16:39:39,192 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.168e+08
2023-07-07 16:39:52,327 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.188e+08
2023-07-07 16:40:05,479 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.00, steps=1.209e+08
2023-07-07 16:40:18,631 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 16:40:31,786 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.00, steps=1.249e+08
2023-07-07 16:40:44,928 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=1.270e+08
2023-07-07 16:40:58,078 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.00, steps=1.290e+08
2023-07-07 16:41:11,244 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 16:41:24,387 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=1.331e+08
2023-07-07 16:41:37,521 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.352e+08
2023-07-07 16:41:50,654 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.00, steps=1.372e+08
2023-07-07 16:42:03,781 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=1.393e+08
2023-07-07 16:42:16,920 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=1.413e+08
2023-07-07 16:42:30,086 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.434e+08
2023-07-07 16:42:43,282 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=1.454e+08
2023-07-07 16:42:56,490 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=1.475e+08
2023-07-07 16:43:09,627 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.495e+08
2023-07-07 16:43:22,759 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=1.516e+08
2023-07-07 16:43:35,892 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.536e+08
2023-07-07 16:43:49,016 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=1.557e+08
2023-07-07 16:44:02,289 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=1.577e+08
2023-07-07 16:44:15,418 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 16:44:28,541 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=1.618e+08
2023-07-07 16:44:41,694 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=1.639e+08
2023-07-07 16:44:54,857 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 16:45:07,987 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.680e+08
2023-07-07 16:45:21,272 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=1.700e+08
2023-07-07 16:45:34,423 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 16:45:47,561 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=1.741e+08
2023-07-07 16:46:00,702 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=1.761e+08
2023-07-07 16:46:13,845 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=1.782e+08
2023-07-07 16:46:26,971 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.802e+08
2023-07-07 16:46:40,122 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.823e+08
2023-07-07 16:46:53,397 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.843e+08
2023-07-07 16:47:06,533 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.864e+08
2023-07-07 16:47:19,675 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.884e+08
2023-07-07 16:47:32,813 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.905e+08
2023-07-07 16:47:46,045 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.925e+08
2023-07-07 16:47:59,185 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=1.946e+08
2023-07-07 16:48:12,314 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 16:48:25,449 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=1.987e+08
2023-07-07 16:48:38,588 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=2.007e+08
2023-07-07 16:48:51,740 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=2.028e+08
2023-07-07 16:49:04,861 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=2.048e+08
2023-07-07 16:49:17,989 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=2.069e+08
2023-07-07 16:49:31,117 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=2.089e+08
2023-07-07 16:49:44,256 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.110e+08
2023-07-07 16:49:57,454 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.130e+08
2023-07-07 16:50:10,591 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.151e+08
2023-07-07 16:50:23,732 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=2.171e+08
2023-07-07 16:50:36,874 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=2.192e+08
2023-07-07 16:50:50,014 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=2.212e+08
2023-07-07 16:51:03,156 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.233e+08
2023-07-07 16:51:16,286 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.253e+08
2023-07-07 16:51:29,412 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.273e+08
2023-07-07 16:51:42,532 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.294e+08
2023-07-07 16:51:55,655 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.314e+08
2023-07-07 16:52:08,792 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=2.335e+08
2023-07-07 16:52:21,945 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=2.355e+08
2023-07-07 16:52:35,098 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=2.376e+08
2023-07-07 16:52:48,251 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=2.396e+08
2023-07-07 16:53:01,401 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=2.417e+08
2023-07-07 16:53:14,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=2.437e+08
2023-07-07 16:53:27,543 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 16:53:27,544 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 16:53:27,568 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:53:27,569 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:53:27,599 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:53:44,941 -        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 16:54:00,623 -        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 16:54:16,335 -        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 16:54:32,036 -        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 16:54:47,743 -        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 16:55:03,468 -        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 16:55:19,163 -        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 16:55:34,853 -        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 16:55:50,537 -        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 16:56:06,227 -        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 16:56:21,912 -        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 16:56:37,587 -        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 16:56:53,263 -        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 16:57:08,959 -        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 16:57:24,642 -        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 16:57:40,339 -        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 16:57:56,022 -        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 16:58:11,711 -        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 16:58:27,391 -        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 16:58:43,096 -        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 16:58:58,779 -        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 16:59:14,474 -        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 16:59:30,160 -        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 16:59:45,881 -        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 17:00:01,586 -        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 17:00:17,285 -        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 17:00:32,989 -        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 17:00:48,716 -        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 17:01:04,439 -        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 17:01:20,138 -        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 17:01:35,832 -        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 17:01:51,533 -        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 17:02:07,251 -        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 17:02:22,946 -        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 17:02:38,643 -        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 17:02:54,334 -        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 17:03:10,018 -        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 17:03:25,702 -        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 17:03:41,388 -        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 17:03:57,081 -        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 17:04:12,767 -        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 17:04:28,461 -        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 17:04:44,143 -        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 17:04:59,839 -        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 17:05:15,523 -        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 17:05:31,209 -        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 17:05:46,899 -        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 17:06:02,604 -        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 17:06:18,301 -        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 17:06:33,995 -        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 17:06:49,711 -        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 17:07:05,413 -        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 17:07:21,124 -        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 17:07:36,829 -        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 17:07:52,564 -        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 17:08:08,399 -        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 17:08:24,169 -        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 17:08:39,896 -        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 17:08:55,713 -        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 17:09:11,451 -        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 17:09:27,167 -        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 17:09:42,882 -        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 17:09:58,574 -        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 17:10:14,269 -        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 17:10:29,987 -        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 17:10:45,692 -        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 17:11:01,383 -        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 17:11:17,078 -        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 17:11:32,765 -        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 17:11:48,447 -        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 17:12:04,135 -        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 17:12:19,828 -        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 17:12:35,522 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.00, steps=1.794e+08
2023-07-07 17:12:51,217 -        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 17:13:06,904 -        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 17:13:22,590 -        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 17:13:38,289 -        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 17:13:53,966 -        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 17:14:09,653 -        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 17:14:25,441 -        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 17:14:41,153 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=1.991e+08
2023-07-07 17:14:56,861 -        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 17:15:12,546 -        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 17:15:28,235 -        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 17:15:43,939 -        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 17:15:59,626 -        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 17:16:15,305 -        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 17:16:30,982 -        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 17:16:46,752 -        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 17:17:02,436 -        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 17:17:18,136 -        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 17:17:33,859 -        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 17:17:49,573 -        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 17:18:05,255 -        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 17:18:20,958 -        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 17:18:36,662 -        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 17:18:52,391 -        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 17:19:08,149 -        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 17:19:23,900 -        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 17:19:39,685 -        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 17:19:55,386 -        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 17:20:11,064 -        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 17:20:26,774 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=2.532e+08
2023-07-07 17:20:42,546 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 17:20:58,239 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10500, best=0.59, avg=0.58, std=0.00, steps=2.581e+08
2023-07-07 17:21:13,928 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10600, best=0.59, avg=0.59, std=0.00, steps=2.605e+08
2023-07-07 17:21:29,602 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10700, best=0.60, avg=0.59, std=0.00, steps=2.630e+08
2023-07-07 17:21:45,322 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10800, best=0.61, avg=0.60, std=0.00, steps=2.654e+08
2023-07-07 17:22:01,154 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10900, best=0.61, avg=0.60, std=0.00, steps=2.679e+08
2023-07-07 17:22:16,841 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11000, best=0.61, avg=0.61, std=0.00, steps=2.704e+08
2023-07-07 17:22:32,532 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11100, best=0.61, avg=0.61, std=0.00, steps=2.728e+08
2023-07-07 17:22:48,231 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11200, best=0.62, avg=0.61, std=0.00, steps=2.753e+08
2023-07-07 17:23:03,930 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11300, best=0.62, avg=0.62, std=0.00, steps=2.777e+08
2023-07-07 17:23:19,617 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11400, best=0.63, avg=0.62, std=0.00, steps=2.802e+08
2023-07-07 17:23:35,361 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11500, best=0.63, avg=0.62, std=0.00, steps=2.826e+08
2023-07-07 17:23:51,109 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11600, best=0.63, avg=0.62, std=0.00, steps=2.851e+08
2023-07-07 17:24:06,814 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11700, best=0.63, avg=0.62, std=0.00, steps=2.876e+08
2023-07-07 17:24:22,545 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11800, best=0.63, avg=0.62, std=0.00, steps=2.900e+08
2023-07-07 17:24:38,352 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11900, best=0.63, avg=0.62, std=0.00, steps=2.925e+08
2023-07-07 17:24:53,947 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11999, best=0.63, avg=0.62, std=0.00, steps=2.949e+08
2023-07-07 17:24:53,948 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 17:24:53,973 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 17:24:53,973 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 17:24:54,006 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 17:25:16,693 -        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 17:25:37,549 -        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 17:25:58,450 -        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 17:26:19,288 -        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 17:26:40,166 -        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 17:27:01,041 -        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 17:27:21,926 -        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 17:27:42,822 -        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 17:28:03,680 -        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 17:28:24,563 -        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 17:28:45,420 -        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 17:29:06,263 -        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 17:29:27,110 -        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 17:29:47,983 -        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 17:30:08,843 -        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 17:30:29,690 -        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 17:30:50,565 -        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 17:31:11,449 -        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 17:31:32,301 -        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 17:31:53,151 -        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 17:32:14,004 -        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 17:32:34,851 -        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 17:32:55,695 -        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 17:33:16,558 -        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 17:33:37,383 -        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 17:33:58,244 -        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 17:34:19,090 -        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 17:34:39,920 -        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 17:35:00,786 -        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 17:35:21,654 -        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 17:35:42,519 -        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 17:36:03,432 -        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 17:36:24,307 -        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 17:36:45,169 -        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 17:37:06,030 -        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 17:37:26,886 -        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 17:37:47,724 -        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 17:38:08,555 -        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 17:38:29,390 -        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 17:38:50,263 -        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 17:39:11,121 -        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 17:39:31,979 -        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 17:39:52,863 -        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 17:40:13,730 -        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 17:40:34,589 -        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 17:40:55,466 -        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 17:41:16,328 -        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 17:41:37,168 -        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 17:41:57,994 -        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 17:42:18,825 -        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 17:42:39,688 -        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 17:43:00,545 -        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 17:43:21,381 -        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 17:43:42,218 -        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 17:44:03,065 -        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 17:44:23,925 -        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 17:44:44,776 -        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 17:45:05,626 -        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 17:45:26,494 -        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 17:45:47,344 -        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 17:46:08,210 -        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 17:46:29,107 -        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 17:46:49,949 -        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 17:47:10,808 -        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 17:47:31,641 -        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 17:47:52,494 -        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 17:48:13,367 -        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 17:48:34,217 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.229e+08
2023-07-07 17:48:55,059 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.261e+08
2023-07-07 17:49:15,921 -        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 17:49:36,773 -        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 17:49:57,615 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.360e+08
2023-07-07 17:50:18,464 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7300, best=0.57, avg=0.57, std=0.00, steps=2.392e+08
2023-07-07 17:50:39,337 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7400, best=0.58, avg=0.57, std=0.00, steps=2.425e+08
2023-07-07 17:51:00,191 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7500, best=0.58, avg=0.57, std=0.00, steps=2.458e+08
2023-07-07 17:51:21,024 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7600, best=0.59, avg=0.59, std=0.00, steps=2.491e+08
2023-07-07 17:51:41,867 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7700, best=0.60, avg=0.60, std=0.00, steps=2.523e+08
2023-07-07 17:52:02,692 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7800, best=0.61, avg=0.60, std=0.00, steps=2.556e+08
2023-07-07 17:52:23,542 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7900, best=0.61, avg=0.60, std=0.00, steps=2.589e+08
2023-07-07 17:52:44,391 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8000, best=0.61, avg=0.61, std=0.00, steps=2.622e+08
2023-07-07 17:53:05,287 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8100, best=0.61, avg=0.61, std=0.00, steps=2.655e+08
2023-07-07 17:53:26,136 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8200, best=0.62, avg=0.61, std=0.00, steps=2.687e+08
2023-07-07 17:53:47,009 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8300, best=0.62, avg=0.61, std=0.00, steps=2.720e+08
2023-07-07 17:54:07,876 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8400, best=0.62, avg=0.62, std=0.00, steps=2.753e+08
2023-07-07 17:54:28,733 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8500, best=0.62, avg=0.62, std=0.00, steps=2.786e+08
2023-07-07 17:54:49,577 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8600, best=0.62, avg=0.62, std=0.00, steps=2.818e+08
2023-07-07 17:55:10,433 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8700, best=0.62, avg=0.62, std=0.00, steps=2.851e+08
2023-07-07 17:55:31,291 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8800, best=0.63, avg=0.62, std=0.00, steps=2.884e+08
2023-07-07 17:55:52,172 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8900, best=0.63, avg=0.62, std=0.00, steps=2.917e+08
2023-07-07 17:56:13,030 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9000, best=0.63, avg=0.62, std=0.00, steps=2.949e+08
2023-07-07 17:56:33,884 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9100, best=0.63, avg=0.62, std=0.00, steps=2.982e+08
2023-07-07 17:56:54,724 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9200, best=0.63, avg=0.62, std=0.00, steps=3.015e+08
2023-07-07 17:57:15,592 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9300, best=0.63, avg=0.63, std=0.00, steps=3.048e+08
2023-07-07 17:57:36,458 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9400, best=0.63, avg=0.63, std=0.00, steps=3.081e+08
2023-07-07 17:57:57,334 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9500, best=0.63, avg=0.63, std=0.00, steps=3.113e+08
2023-07-07 17:58:18,222 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9600, best=0.63, avg=0.63, std=0.00, steps=3.146e+08
2023-07-07 17:58:39,049 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9700, best=0.64, avg=0.63, std=0.00, steps=3.179e+08
2023-07-07 17:58:59,890 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9800, best=0.64, avg=0.63, std=0.00, steps=3.212e+08
2023-07-07 17:59:20,756 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9900, best=0.64, avg=0.63, std=0.00, steps=3.244e+08
2023-07-07 17:59:41,607 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10000, best=0.64, avg=0.63, std=0.00, steps=3.277e+08
2023-07-07 18:00:02,435 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10100, best=0.64, avg=0.63, std=0.00, steps=3.310e+08
2023-07-07 18:00:23,282 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10200, best=0.64, avg=0.64, std=0.00, steps=3.343e+08
2023-07-07 18:00:44,155 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10300, best=0.64, avg=0.64, std=0.00, steps=3.375e+08
2023-07-07 18:01:05,037 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10400, best=0.64, avg=0.64, std=0.00, steps=3.408e+08
2023-07-07 18:01:25,904 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10500, best=0.64, avg=0.64, std=0.00, steps=3.441e+08
2023-07-07 18:01:46,744 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10600, best=0.64, avg=0.64, std=0.00, steps=3.474e+08
2023-07-07 18:02:07,601 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10700, best=0.64, avg=0.64, std=0.00, steps=3.507e+08
2023-07-07 18:02:28,456 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10800, best=0.64, avg=0.64, std=0.00, steps=3.539e+08
2023-07-07 18:02:49,314 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10900, best=0.64, avg=0.64, std=0.00, steps=3.572e+08
2023-07-07 18:03:10,175 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11000, best=0.65, avg=0.64, std=0.00, steps=3.605e+08
2023-07-07 18:03:31,054 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11100, best=0.65, avg=0.64, std=0.00, steps=3.638e+08
2023-07-07 18:03:51,907 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11200, best=0.65, avg=0.64, std=0.00, steps=3.670e+08
2023-07-07 18:04:12,753 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11300, best=0.65, avg=0.64, std=0.00, steps=3.703e+08
2023-07-07 18:04:33,610 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11400, best=0.65, avg=0.64, std=0.00, steps=3.736e+08
2023-07-07 18:04:54,483 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11500, best=0.65, avg=0.64, std=0.00, steps=3.769e+08
2023-07-07 18:05:15,318 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11600, best=0.65, avg=0.64, std=0.00, steps=3.801e+08
2023-07-07 18:05:36,179 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11700, best=0.65, avg=0.64, std=0.00, steps=3.834e+08
2023-07-07 18:05:57,055 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11800, best=0.65, avg=0.65, std=0.00, steps=3.867e+08
2023-07-07 18:06:17,947 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11900, best=0.65, avg=0.65, std=0.00, steps=3.900e+08
2023-07-07 18:06:38,643 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11999, best=0.65, avg=0.65, std=0.00, steps=3.932e+08
2023-07-07 18:06:38,643 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 18:06:38,669 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:06:38,669 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:06:38,701 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:07:02,643 -        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 18:07:24,770 -        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 18:07:46,916 -        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 18:08:09,054 -        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 18:08:31,173 -        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 18:08:53,302 -        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 18:09:15,418 -        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 18:09:37,543 -        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 18:09:59,664 -        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 18:10:21,814 -        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 18:10:43,913 -        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 18:11:06,034 -        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 18:11:28,147 -        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 18:11:50,236 -        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 18:12:12,342 -        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 18:12:34,448 -        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 18:12:56,567 -        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 18:13:18,681 -        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 18:13:40,794 -        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 18:14:02,927 -        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 18:14:25,064 -        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 18:14:47,192 -        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 18:15:09,323 -        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 18:15:31,440 -        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 18:15:53,561 -        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 18:16:15,675 -        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 18:16:37,788 -        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 18:16:59,921 -        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 18:17:22,063 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.00, steps=1.010e+08
2023-07-07 18:17:44,217 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.045e+08
2023-07-07 18:18:06,327 -        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 18:18:28,471 -        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 18:18:50,634 -        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 18:19:12,738 -        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 18:19:34,848 -        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 18:19:56,980 -        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 18:20:19,112 -        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 18:20:41,201 -        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 18:21:03,337 -        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 18:21:25,485 -        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 18:21:47,616 -        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 18:22:09,738 -        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 18:22:31,872 -        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 18:22:53,990 -        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 18:23:16,100 -        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 18:23:38,222 -        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 18:24:00,362 -        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 18:24:22,455 -        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 18:24:44,564 -        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 18:25:06,707 -        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 18:25:28,854 -        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 18:25:50,988 -        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 18:26:13,117 -        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 18:26:35,226 -        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 18:26:57,331 -        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 18:27:19,487 -        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 18:27:41,629 -        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 18:28:03,774 -        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 18:28:25,887 -        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 18:28:48,013 -        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 18:29:10,130 -        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 18:29:32,246 -        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 18:29:54,371 -        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 18:30:16,496 -        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 18:30:38,630 -        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 18:31:00,745 -        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 18:31:22,861 -        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 18:31:44,970 -        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 18:32:07,122 -        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 18:32:29,245 -        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 18:32:51,367 -        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 18:33:13,477 -        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 18:33:35,603 -        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 18:33:57,722 -        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 18:34:19,840 -        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 18:34:41,933 -        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 18:35:04,070 -        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 18:35:26,178 -        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 18:35:48,277 -        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 18:36:10,369 -        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 18:36:32,499 -        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 18:36:54,611 -        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 18:37:16,738 -        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 18:37:38,878 -        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 18:38:00,987 -        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 18:38:23,102 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.995e+08
2023-07-07 18:38:45,198 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=3.029e+08
2023-07-07 18:39:07,335 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=3.064e+08
2023-07-07 18:39:29,467 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=3.099e+08
2023-07-07 18:39:51,579 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=3.134e+08
2023-07-07 18:40:13,708 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.169e+08
2023-07-07 18:40:35,841 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.203e+08
2023-07-07 18:40:57,986 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.238e+08
2023-07-07 18:41:20,129 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.273e+08
2023-07-07 18:41:42,253 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.308e+08
2023-07-07 18:42:04,381 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 18:42:26,491 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.378e+08
2023-07-07 18:42:48,618 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.412e+08
2023-07-07 18:43:10,758 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.447e+08
2023-07-07 18:43:32,868 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.482e+08
2023-07-07 18:43:54,986 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.517e+08
2023-07-07 18:44:17,106 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.552e+08
2023-07-07 18:44:39,238 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.586e+08
2023-07-07 18:45:01,337 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.621e+08
2023-07-07 18:45:23,481 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.656e+08
2023-07-07 18:45:45,625 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.691e+08
2023-07-07 18:46:07,758 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.726e+08
2023-07-07 18:46:29,941 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 18:46:52,095 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=3.795e+08
2023-07-07 18:47:14,202 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=3.830e+08
2023-07-07 18:47:36,306 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=3.865e+08
2023-07-07 18:47:58,400 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=3.900e+08
2023-07-07 18:48:20,507 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=3.935e+08
2023-07-07 18:48:42,609 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=3.969e+08
2023-07-07 18:49:04,704 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.004e+08
2023-07-07 18:49:26,805 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.039e+08
2023-07-07 18:49:48,949 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.074e+08
2023-07-07 18:50:11,078 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.109e+08
2023-07-07 18:50:33,251 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.143e+08
2023-07-07 18:50:55,159 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.178e+08
2023-07-07 18:50:55,160 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 18:50:55,185 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:50:55,185 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:50:55,216 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:51:20,421 -        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 18:51:43,816 -        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 18:52:07,223 -        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 18:52:30,620 -        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 18:52:54,013 -        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 18:53:17,429 -        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 18:53:40,828 -        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 18:54:04,233 -        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 18:54:27,660 -        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 18:54:51,062 -        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 18:55:14,459 -        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 18:55:37,866 -        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 18:56:01,273 -        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 18:56:24,682 -        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 18:56:48,077 -        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 18:57:11,463 -        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 18:57:34,866 -        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 18:57:58,275 -        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 18:58:21,694 -        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 18:58:45,089 -        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 18:59:08,502 -        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 18:59:31,903 -        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 18:59:55,324 -        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 19:00:18,723 -        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 19:00:42,103 -        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 19:01:05,503 -        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 19:01:28,897 -        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 19:01:52,327 -        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 19:02:15,771 -        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 19:02:39,210 -        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 19:03:02,635 -        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 19:03:26,028 -        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 19:03:49,408 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 19:04:12,831 -        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 19:04:36,226 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3500, best=0.50, avg=0.50, std=0.00, steps=1.291e+08
2023-07-07 19:04:59,660 -        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 19:05:23,062 -        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 19:05:46,467 -        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 19:06:09,860 -        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 19:06:33,242 -        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 19:06:56,657 -        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 19:07:20,032 -        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 19:07:43,433 -        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 19:08:06,825 -        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 19:08:30,212 -        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 19:08:53,633 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4600, best=0.50, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 19:09:17,008 -        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 19:09:40,406 -        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 19:10:03,830 -        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 19:10:27,260 -        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 19:10:50,685 -        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 19:11:14,101 -        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 19:11:37,507 -        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 19:12:00,919 -        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 19:12:24,348 -        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 19:12:47,755 -        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 19:13:11,154 -        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 19:13:34,554 -        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 19:13:57,971 -        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 19:14:21,363 -        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 19:14:44,785 -        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 19:15:08,215 -        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 19:15:31,610 -        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 19:15:55,007 -        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 19:16:18,409 -        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 19:16:41,806 -        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 19:17:05,203 -        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 19:17:28,614 -        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 19:17:52,016 -        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 19:18:15,454 -        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 19:18:38,835 -        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 19:19:02,228 -        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 19:19:25,614 -        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 19:19:49,017 -        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 19:20:12,415 -        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 19:20:35,822 -        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 19:20:59,195 -        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 19:21:22,593 -        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 19:21:45,996 -        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 19:22:09,381 -        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 19:22:32,801 -        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 19:22:56,202 -        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 19:23:19,578 -        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 19:23:42,975 -        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 19:24:06,373 -        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 19:24:29,751 -        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 19:24:53,153 -        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 19:25:16,536 -        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 19:25:39,920 -        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 19:26:03,323 -        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 19:26:26,735 -        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 19:26:50,115 -        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 19:27:13,494 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.429e+08
2023-07-07 19:27:36,882 -        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 19:28:00,262 -        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 19:28:23,658 -        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 19:28:47,070 -        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 19:29:10,490 -        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 19:29:33,914 -        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 19:29:57,293 -        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 19:30:20,707 -        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 19:30:44,100 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.760e+08
2023-07-07 19:31:07,487 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.797e+08
2023-07-07 19:31:30,895 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.834e+08
2023-07-07 19:31:54,335 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.871e+08
2023-07-07 19:32:17,765 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.908e+08
2023-07-07 19:32:41,154 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=3.945e+08
2023-07-07 19:33:04,565 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=3.982e+08
2023-07-07 19:33:27,998 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=4.019e+08
2023-07-07 19:33:51,402 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 19:34:14,792 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=4.092e+08
2023-07-07 19:34:38,178 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=4.129e+08
2023-07-07 19:35:01,588 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=4.166e+08
2023-07-07 19:35:25,015 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=4.203e+08
2023-07-07 19:35:48,423 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=4.240e+08
2023-07-07 19:36:11,827 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=4.277e+08
2023-07-07 19:36:35,268 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=4.313e+08
2023-07-07 19:36:58,650 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=4.350e+08
2023-07-07 19:37:22,054 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=4.387e+08
2023-07-07 19:37:45,248 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=4.424e+08
2023-07-07 19:37:45,249 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
2023-07-07 19:37:45,274 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 19:37:45,274 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 19:37:45,305 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 19:38:13,112 -        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 19:38:39,041 -        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 19:39:04,975 -        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 19:39:30,947 -        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 19:39:56,896 -        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 19:40:22,856 -        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 19:40:48,806 -        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 19:41:14,772 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=3.281e+07
2023-07-07 19:41:40,750 -        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 19:42:06,675 -        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 19:42:32,631 -        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 19:42:58,618 -        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 19:43:24,592 -        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 19:43:50,534 -        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 19:44:16,500 -        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 19:44:42,476 -        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 19:45:08,443 -        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 19:45:34,402 -        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 19:46:00,380 -        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 19:46:26,336 -        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 19:46:52,277 -        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 19:47:18,217 -        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 19:47:44,196 -        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 19:48:10,152 -        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 19:48:36,112 -        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 19:49:02,069 -        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 19:49:28,051 -        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 19:49:53,985 -        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 19:50:19,936 -        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 19:50:45,951 -        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 19:51:11,921 -        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 19:51:37,878 -        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 19:52:03,854 -        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 19:52:29,791 -        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 19:52:55,748 -        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 19:53:21,691 -        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 19:53:47,633 -        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 19:54:13,612 -        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 19:54:39,561 -        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 19:55:05,490 -        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 19:55:31,468 -        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 19:55:57,498 -        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 19:56:23,519 -        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 19:56:49,508 -        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 19:57:15,481 -        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 19:57:41,492 -        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 19:58:07,428 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.926e+08
2023-07-07 19:58:33,421 -        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 19:58:59,376 -        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 19:59:25,322 -        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 19:59:51,258 -        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 20:00:17,212 -        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 20:00:43,197 -        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 20:01:09,163 -        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 20:01:35,097 -        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 20:02:01,050 -        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 20:02:27,015 -        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 20:02:53,046 -        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 20:03:19,015 -        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 20:03:44,949 -        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 20:04:10,901 -        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 20:04:36,874 -        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 20:05:02,838 -        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 20:05:28,790 -        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 20:05:54,730 -        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 20:06:20,692 -        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 20:06:46,633 -        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 20:07:12,565 -        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 20:07:38,505 -        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 20:08:04,484 -        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 20:08:30,484 -        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 20:08:56,461 -        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 20:09:22,413 -        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 20:09:48,399 -        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 20:10:14,357 -        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 20:10:40,330 -        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 20:11:06,297 -        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 20:11:32,245 -        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 20:11:58,197 -        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 20:12:24,143 -        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 20:12:50,125 -        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 20:13:16,115 -        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 20:13:42,094 -        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 20:14:08,060 -        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 20:14:34,010 -        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 20:14:59,973 -        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 20:15:25,989 -        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 20:15:51,966 -        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 20:16:17,890 -        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 20:16:43,876 -        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 20:17:09,823 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9100, best=0.50, avg=0.50, std=0.00, steps=3.728e+08
2023-07-07 20:17:35,797 -        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 20:18:01,751 -        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 20:18:27,724 -        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 20:18:53,712 -        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 20:19:19,650 -        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 20:19:45,586 -        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 20:20:11,563 -        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 20:20:37,512 -        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 20:21:03,451 -        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 20:21:29,419 -        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 20:21:55,362 -        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 20:22:21,320 -        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 20:22:47,279 -        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 20:23:13,268 -        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 20:23:39,208 -        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 20:24:05,178 -        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 20:24:31,139 -        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 20:24:57,110 -        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 20:25:23,056 -        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 20:25:49,031 -        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 20:26:14,961 -        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 20:26:40,937 -        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 20:27:06,931 -        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 20:27:32,903 -        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 20:27:58,861 -        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 20:28:24,823 -        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 20:28:50,791 -        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 20:29:16,754 -        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 20:29:42,538 -        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 20:29:42,539 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135934
