2023-07-07 13:58:29,946 -        meta learning: [    INFO] - [INFO] checkpoint saved to: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 13:58:29,946 -        meta learning: [    INFO] - [INFO] tensorboard dir set to: ./runs/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 13:58:29,946 -        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=36, 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--20230707-135829', summary_writer=<torch.utils.tensorboard.writer.SummaryWriter object at 0x7fca8c25fd90>, tb_prefix='PGPE/SeqTask/GruPolicy')
2023-07-07 13:58:33,067 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 13:58:33,067 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 13:58:33,135 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 13:58:39,461 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 100, best=0.52, avg=0.50, std=0.01, steps=4.137e+05
2023-07-07 13:58:42,369 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 200, best=0.53, avg=0.50, std=0.01, steps=8.233e+05
2023-07-07 13:58:45,227 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=1.233e+06
2023-07-07 13:58:48,070 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 400, best=0.52, avg=0.50, std=0.01, steps=1.642e+06
2023-07-07 13:58:50,924 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=2.052e+06
2023-07-07 13:58:53,786 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=2.462e+06
2023-07-07 13:58:56,655 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=2.871e+06
2023-07-07 13:58:59,546 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 800, best=0.52, avg=0.50, std=0.01, steps=3.281e+06
2023-07-07 13:59:02,462 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=3.690e+06
2023-07-07 13:59:05,385 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=4.100e+06
2023-07-07 13:59:08,263 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=4.510e+06
2023-07-07 13:59:11,176 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=4.919e+06
2023-07-07 13:59:14,049 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1300, best=0.52, avg=0.50, std=0.01, steps=5.329e+06
2023-07-07 13:59:16,912 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=5.738e+06
2023-07-07 13:59:19,777 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=6.148e+06
2023-07-07 13:59:22,641 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=6.558e+06
2023-07-07 13:59:25,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=6.967e+06
2023-07-07 13:59:28,423 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=7.377e+06
2023-07-07 13:59:31,304 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=7.786e+06
2023-07-07 13:59:34,191 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=8.196e+06
2023-07-07 13:59:37,101 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=8.606e+06
2023-07-07 13:59:39,972 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=9.015e+06
2023-07-07 13:59:42,824 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=9.425e+06
2023-07-07 13:59:45,699 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=9.834e+06
2023-07-07 13:59:48,566 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.024e+07
2023-07-07 13:59:51,422 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.065e+07
2023-07-07 13:59:54,282 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.106e+07
2023-07-07 13:59:57,138 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.01, steps=1.147e+07
2023-07-07 13:59:59,994 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.188e+07
2023-07-07 14:00:02,854 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 14:00:05,713 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=1.270e+07
2023-07-07 14:00:08,572 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.311e+07
2023-07-07 14:00:11,418 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 14:00:14,267 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=1.393e+07
2023-07-07 14:00:17,134 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=1.434e+07
2023-07-07 14:00:19,990 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 14:00:22,846 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=1.516e+07
2023-07-07 14:00:25,703 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=1.557e+07
2023-07-07 14:00:28,559 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 14:00:31,406 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=1.639e+07
2023-07-07 14:00:34,277 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=1.680e+07
2023-07-07 14:00:37,122 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 14:00:40,007 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=1.762e+07
2023-07-07 14:00:42,859 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 14:00:45,722 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 14:00:48,576 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=1.885e+07
2023-07-07 14:00:51,427 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=1.926e+07
2023-07-07 14:00:54,278 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4800, best=0.53, avg=0.50, std=0.01, steps=1.966e+07
2023-07-07 14:00:57,143 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=2.007e+07
2023-07-07 14:01:00,002 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=2.048e+07
2023-07-07 14:01:02,860 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=2.089e+07
2023-07-07 14:01:05,716 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=2.130e+07
2023-07-07 14:01:08,572 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=2.171e+07
2023-07-07 14:01:11,434 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 14:01:14,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=2.253e+07
2023-07-07 14:01:17,137 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=2.294e+07
2023-07-07 14:01:19,995 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 14:01:22,855 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=2.376e+07
2023-07-07 14:01:25,725 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=2.417e+07
2023-07-07 14:01:28,582 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 14:01:31,443 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=2.499e+07
2023-07-07 14:01:34,308 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=2.540e+07
2023-07-07 14:01:37,164 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 14:01:40,021 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6400, best=0.53, avg=0.50, std=0.01, steps=2.622e+07
2023-07-07 14:01:42,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=2.663e+07
2023-07-07 14:01:45,739 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 14:01:48,608 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=2.745e+07
2023-07-07 14:01:51,472 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 14:01:54,330 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 14:01:57,192 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 14:02:00,049 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=2.909e+07
2023-07-07 14:02:02,907 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 14:02:05,763 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.01, steps=2.990e+07
2023-07-07 14:02:08,620 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7400, best=0.71, avg=0.70, std=0.01, steps=3.031e+07
2023-07-07 14:02:11,479 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7500, best=0.77, avg=0.75, std=0.01, steps=3.072e+07
2023-07-07 14:02:14,339 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7600, best=0.80, avg=0.78, std=0.01, steps=3.113e+07
2023-07-07 14:02:17,199 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7700, best=0.83, avg=0.81, std=0.01, steps=3.154e+07
2023-07-07 14:02:20,053 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7800, best=0.86, avg=0.84, std=0.01, steps=3.195e+07
2023-07-07 14:02:22,908 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 7900, best=0.88, avg=0.86, std=0.01, steps=3.236e+07
2023-07-07 14:02:25,767 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8000, best=0.89, avg=0.87, std=0.01, steps=3.277e+07
2023-07-07 14:02:28,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8100, best=0.91, avg=0.90, std=0.00, steps=3.318e+07
2023-07-07 14:02:31,480 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8200, best=0.92, avg=0.91, std=0.01, steps=3.359e+07
2023-07-07 14:02:34,346 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8300, best=0.93, avg=0.92, std=0.00, steps=3.400e+07
2023-07-07 14:02:37,210 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8400, best=0.93, avg=0.92, std=0.00, steps=3.441e+07
2023-07-07 14:02:40,072 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8500, best=0.94, avg=0.94, std=0.00, steps=3.482e+07
2023-07-07 14:02:42,927 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8600, best=0.95, avg=0.95, std=0.00, steps=3.523e+07
2023-07-07 14:02:45,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8700, best=0.96, avg=0.95, std=0.00, steps=3.564e+07
2023-07-07 14:02:48,651 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8800, best=0.96, avg=0.95, std=0.00, steps=3.605e+07
2023-07-07 14:02:51,518 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 8900, best=0.96, avg=0.95, std=0.00, steps=3.646e+07
2023-07-07 14:02:54,381 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9000, best=0.96, avg=0.95, std=0.00, steps=3.687e+07
2023-07-07 14:02:57,238 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9100, best=0.96, avg=0.95, std=0.00, steps=3.728e+07
2023-07-07 14:03:00,100 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9200, best=0.96, avg=0.95, std=0.00, steps=3.769e+07
2023-07-07 14:03:02,963 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9300, best=0.96, avg=0.95, std=0.00, steps=3.810e+07
2023-07-07 14:03:05,831 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9400, best=0.99, avg=0.98, std=0.00, steps=3.851e+07
2023-07-07 14:03:08,694 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9500, best=1.00, avg=0.99, std=0.00, steps=3.892e+07
2023-07-07 14:03:11,554 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 0, 0, [Train]: 9600, best=1.00, avg=0.99, std=0.00, steps=3.933e+07
2023-07-07 14:03:14,427 -        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 14:03:17,289 -        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 14:03:20,159 -        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 14:03:23,028 -        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 14:03:25,890 -        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 14:03:28,761 -        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 14:03:31,611 -        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 14:03:34,471 -        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 14:03:37,322 -        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 14:03:40,179 -        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 14:03:43,034 -        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 14:03:45,894 -        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 14:03:48,789 -        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 14:03:51,667 -        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 14:03:54,522 -        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 14:03:57,390 -        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 14:04:00,251 -        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 14:04:03,114 -        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 14:04:05,970 -        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 14:04:08,829 -        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 14:04:11,694 -        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 14:04:14,557 -        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 14:04:17,416 -        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 14:04:20,248 -        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 14:04:20,248 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 14:04:20,273 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:04:20,274 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:04:20,305 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:04:26,039 -        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 14:04:30,196 -        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 14:04:34,347 -        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 14:04:38,497 -        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 14:04:42,658 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=3.078e+06
2023-07-07 14:04:46,807 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 600, best=0.53, avg=0.50, std=0.01, steps=3.693e+06
2023-07-07 14:04:50,964 -        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 14:04:55,117 -        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 14:04:59,268 -        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 14:05:03,420 -        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 14:05:07,573 -        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 14:05:11,730 -        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 14:05:15,867 -        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 14:05:20,018 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1400, best=0.53, avg=0.50, std=0.01, steps=8.608e+06
2023-07-07 14:05:24,178 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=9.222e+06
2023-07-07 14:05:28,331 -        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 14:05:32,486 -        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 14:05:36,639 -        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 14:05:40,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 1900, best=0.53, avg=0.50, std=0.01, steps=1.168e+07
2023-07-07 14:05:44,960 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=1.229e+07
2023-07-07 14:05:49,132 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=1.291e+07
2023-07-07 14:05:53,280 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.352e+07
2023-07-07 14:05:57,418 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=1.414e+07
2023-07-07 14:06:01,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 14:06:05,708 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=1.537e+07
2023-07-07 14:06:09,851 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=1.598e+07
2023-07-07 14:06:14,009 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=1.659e+07
2023-07-07 14:06:18,150 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=1.721e+07
2023-07-07 14:06:22,286 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 2900, best=0.52, avg=0.50, std=0.01, steps=1.782e+07
2023-07-07 14:06:26,428 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 14:06:30,568 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3100, best=0.53, avg=0.50, std=0.01, steps=1.905e+07
2023-07-07 14:06:34,737 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=1.967e+07
2023-07-07 14:06:38,881 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=2.028e+07
2023-07-07 14:06:43,029 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 14:06:47,165 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 14:06:51,297 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.212e+07
2023-07-07 14:06:55,441 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3700, best=0.52, avg=0.50, std=0.01, steps=2.274e+07
2023-07-07 14:06:59,599 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=2.335e+07
2023-07-07 14:07:03,742 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=2.397e+07
2023-07-07 14:07:07,880 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=2.458e+07
2023-07-07 14:07:12,037 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=2.520e+07
2023-07-07 14:07:16,187 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4200, best=0.53, avg=0.50, std=0.01, steps=2.581e+07
2023-07-07 14:07:20,350 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=2.643e+07
2023-07-07 14:07:24,504 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=2.704e+07
2023-07-07 14:07:28,665 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=2.765e+07
2023-07-07 14:07:32,822 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 14:07:36,973 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4700, best=0.52, avg=0.50, std=0.01, steps=2.888e+07
2023-07-07 14:07:41,127 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 14:07:45,279 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=3.011e+07
2023-07-07 14:07:49,438 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 14:07:53,586 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=3.134e+07
2023-07-07 14:07:57,730 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5200, best=0.52, avg=0.50, std=0.01, steps=3.195e+07
2023-07-07 14:08:01,876 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5300, best=0.52, avg=0.50, std=0.01, steps=3.257e+07
2023-07-07 14:08:06,018 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=3.318e+07
2023-07-07 14:08:10,157 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5500, best=0.52, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 14:08:14,305 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=3.441e+07
2023-07-07 14:08:18,448 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5700, best=0.52, avg=0.50, std=0.01, steps=3.503e+07
2023-07-07 14:08:22,593 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=3.564e+07
2023-07-07 14:08:26,738 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=3.626e+07
2023-07-07 14:08:30,880 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:08:35,027 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=3.748e+07
2023-07-07 14:08:39,173 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=3.810e+07
2023-07-07 14:08:43,333 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=3.871e+07
2023-07-07 14:08:47,477 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 14:08:51,624 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=3.994e+07
2023-07-07 14:08:55,770 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 14:08:59,913 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=4.117e+07
2023-07-07 14:09:04,063 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=4.179e+07
2023-07-07 14:09:08,220 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 6900, best=0.52, avg=0.50, std=0.01, steps=4.240e+07
2023-07-07 14:09:12,364 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=4.301e+07
2023-07-07 14:09:16,509 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=4.363e+07
2023-07-07 14:09:20,646 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7200, best=0.52, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 14:09:24,789 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7300, best=0.52, avg=0.50, std=0.01, steps=4.486e+07
2023-07-07 14:09:28,957 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=4.547e+07
2023-07-07 14:09:33,111 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=4.609e+07
2023-07-07 14:09:37,266 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7600, best=0.52, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 14:09:41,417 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=4.731e+07
2023-07-07 14:09:45,565 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7800, best=0.53, avg=0.50, std=0.01, steps=4.793e+07
2023-07-07 14:09:49,707 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=4.854e+07
2023-07-07 14:09:53,862 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:09:58,017 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=4.977e+07
2023-07-07 14:10:02,170 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 14:10:06,325 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=5.100e+07
2023-07-07 14:10:10,478 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8400, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:10:14,644 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=5.223e+07
2023-07-07 14:10:18,813 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=5.284e+07
2023-07-07 14:10:22,955 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=5.346e+07
2023-07-07 14:10:27,088 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=5.407e+07
2023-07-07 14:10:31,230 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=5.469e+07
2023-07-07 14:10:35,372 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=5.530e+07
2023-07-07 14:10:39,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=5.592e+07
2023-07-07 14:10:43,666 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=5.653e+07
2023-07-07 14:10:47,831 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=5.715e+07
2023-07-07 14:10:51,982 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=5.776e+07
2023-07-07 14:10:56,138 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=5.837e+07
2023-07-07 14:11:00,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=5.899e+07
2023-07-07 14:11:04,441 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9700, best=0.53, avg=0.50, std=0.01, steps=5.960e+07
2023-07-07 14:11:08,579 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=6.022e+07
2023-07-07 14:11:12,732 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=6.083e+07
2023-07-07 14:11:16,869 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 14:11:21,025 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=6.206e+07
2023-07-07 14:11:25,169 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=6.267e+07
2023-07-07 14:11:29,314 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=6.329e+07
2023-07-07 14:11:33,455 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=6.390e+07
2023-07-07 14:11:37,597 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=6.452e+07
2023-07-07 14:11:41,767 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=6.513e+07
2023-07-07 14:11:45,914 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10700, best=0.52, avg=0.50, std=0.01, steps=6.575e+07
2023-07-07 14:11:50,062 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10800, best=0.52, avg=0.50, std=0.01, steps=6.636e+07
2023-07-07 14:11:54,211 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 10900, best=0.52, avg=0.50, std=0.01, steps=6.698e+07
2023-07-07 14:11:58,358 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11000, best=0.52, avg=0.50, std=0.01, steps=6.759e+07
2023-07-07 14:12:02,506 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11100, best=0.52, avg=0.50, std=0.01, steps=6.820e+07
2023-07-07 14:12:06,659 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.01, steps=6.882e+07
2023-07-07 14:12:10,804 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11300, best=0.52, avg=0.50, std=0.01, steps=6.943e+07
2023-07-07 14:12:14,944 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11400, best=0.52, avg=0.50, std=0.01, steps=7.005e+07
2023-07-07 14:12:19,083 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11500, best=0.52, avg=0.50, std=0.01, steps=7.066e+07
2023-07-07 14:12:23,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11600, best=0.71, avg=0.69, std=0.01, steps=7.128e+07
2023-07-07 14:12:27,374 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11700, best=0.74, avg=0.73, std=0.01, steps=7.189e+07
2023-07-07 14:12:31,511 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11800, best=0.77, avg=0.76, std=0.01, steps=7.251e+07
2023-07-07 14:12:35,653 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11900, best=0.77, avg=0.76, std=0.01, steps=7.312e+07
2023-07-07 14:12:39,759 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 8, 0, [Train]: 11999, best=0.78, avg=0.77, std=0.01, steps=7.373e+07
2023-07-07 14:12:39,760 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 14:12:39,784 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:12:39,785 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:12:39,815 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:12:46,851 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 100, best=0.53, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 14:12:52,297 -        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 14:12:57,741 -        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 14:13:03,191 -        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 14:13:08,613 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 14:13:14,068 -        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 14:13:19,522 -        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 14:13:24,959 -        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 14:13:30,397 -        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 14:13:35,875 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=8.200e+06
2023-07-07 14:13:41,330 -        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 14:13:46,783 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=9.839e+06
2023-07-07 14:13:52,238 -        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 14:13:57,688 -        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 14:14:03,122 -        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 14:14:08,559 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1600, best=0.52, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 14:14:14,009 -        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 14:14:19,460 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 14:14:24,934 -        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 14:14:30,398 -        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 14:14:35,856 -        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 14:14:41,287 -        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 14:14:46,723 -        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 14:14:52,158 -        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 14:14:57,603 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 2500, best=0.53, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 14:15:03,036 -        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 14:15:08,481 -        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 14:15:13,935 -        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 14:15:19,384 -        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 14:15:24,836 -        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 14:15:30,290 -        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 14:15:35,734 -        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 14:15:41,173 -        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 14:15:46,606 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 3400, best=0.52, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 14:15:52,039 -        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 14:15:57,477 -        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 14:16:02,933 -        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 14:16:08,409 -        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 14:16:13,865 -        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 14:16:19,339 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:16:24,817 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=3.360e+07
2023-07-07 14:16:30,271 -        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 14:16:35,746 -        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 14:16:41,200 -        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 14:16:46,665 -        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 14:16:52,121 -        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 14:16:57,576 -        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 14:17:03,025 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4800, best=0.53, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 14:17:08,469 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=4.015e+07
2023-07-07 14:17:13,907 -        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 14:17:19,339 -        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 14:17:24,784 -        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 14:17:30,234 -        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 14:17:35,675 -        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 14:17:41,125 -        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 14:17:46,580 -        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 14:17:52,024 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5700, best=0.53, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 14:17:57,492 -        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 14:18:02,937 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 5900, best=0.53, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 14:18:08,366 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6000, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:18:13,797 -        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 14:18:19,241 -        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 14:18:24,687 -        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 14:18:30,139 -        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 14:18:35,603 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6500, best=0.52, avg=0.50, std=0.01, steps=5.326e+07
2023-07-07 14:18:41,048 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6600, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 14:18:46,495 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 6700, best=0.53, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 14:18:51,939 -        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 14:18:57,396 -        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 14:19:02,839 -        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 14:19:08,278 -        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 14:19:13,716 -        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 14:19:19,163 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7300, best=0.53, avg=0.50, std=0.01, steps=5.981e+07
2023-07-07 14:19:24,601 -        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 14:19:30,035 -        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 14:19:35,461 -        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 14:19:40,904 -        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 14:19:46,335 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 14:19:51,777 -        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 14:19:57,228 -        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 14:20:02,664 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8100, best=0.53, avg=0.50, std=0.01, steps=6.636e+07
2023-07-07 14:20:08,111 -        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 14:20:13,554 -        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 14:20:19,008 -        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 14:20:24,466 -        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 14:20:29,905 -        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 14:20:35,350 -        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 14:20:40,794 -        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 14:20:46,236 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.01, steps=7.292e+07
2023-07-07 14:20:51,666 -        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 14:20:57,114 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9100, best=0.53, avg=0.50, std=0.01, steps=7.456e+07
2023-07-07 14:21:02,561 -        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 14:21:07,995 -        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 14:21:13,503 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=7.701e+07
2023-07-07 14:21:18,942 -        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 14:21:24,386 -        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 14:21:29,825 -        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 14:21:35,274 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=8.029e+07
2023-07-07 14:21:40,707 -        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 14:21:46,150 -        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 14:21:51,596 -        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 14:21:57,038 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10200, best=0.53, avg=0.50, std=0.01, steps=8.357e+07
2023-07-07 14:22:02,479 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10300, best=0.53, avg=0.50, std=0.01, steps=8.439e+07
2023-07-07 14:22:07,916 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=8.520e+07
2023-07-07 14:22:13,345 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=8.602e+07
2023-07-07 14:22:18,804 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=8.684e+07
2023-07-07 14:22:24,243 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10700, best=0.52, avg=0.50, std=0.01, steps=8.766e+07
2023-07-07 14:22:29,702 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10800, best=0.52, avg=0.50, std=0.01, steps=8.848e+07
2023-07-07 14:22:35,147 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 10900, best=0.52, avg=0.50, std=0.01, steps=8.930e+07
2023-07-07 14:22:40,592 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11000, best=0.52, avg=0.50, std=0.01, steps=9.012e+07
2023-07-07 14:22:46,044 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11100, best=0.52, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 14:22:51,501 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.01, steps=9.176e+07
2023-07-07 14:22:56,978 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11300, best=0.53, avg=0.50, std=0.01, steps=9.258e+07
2023-07-07 14:23:02,427 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11400, best=0.52, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 14:23:07,878 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11500, best=0.53, avg=0.50, std=0.01, steps=9.422e+07
2023-07-07 14:23:13,318 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11600, best=0.52, avg=0.50, std=0.01, steps=9.504e+07
2023-07-07 14:23:18,780 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11700, best=0.52, avg=0.50, std=0.01, steps=9.585e+07
2023-07-07 14:23:24,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11800, best=0.52, avg=0.50, std=0.01, steps=9.667e+07
2023-07-07 14:23:29,674 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11900, best=0.52, avg=0.50, std=0.01, steps=9.749e+07
2023-07-07 14:23:35,057 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 16, 0, [Train]: 11999, best=0.52, avg=0.50, std=0.01, steps=9.830e+07
2023-07-07 14:23:35,058 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 14:23:35,088 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:23:35,089 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:23:35,126 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:23:44,732 -        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 14:23:52,740 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=2.470e+06
2023-07-07 14:24:00,729 -        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 14:24:08,740 -        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 14:24:16,768 -        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 14:24:24,793 -        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 14:24:32,794 -        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 14:24:40,822 -        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 14:24:48,859 -        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 14:24:56,941 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1000, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:25:04,987 -        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 14:25:13,013 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1200, best=0.53, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 14:25:21,020 -        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 14:25:29,038 -        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 14:25:37,040 -        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 14:25:45,041 -        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 14:25:53,046 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 1700, best=0.52, avg=0.50, std=0.01, steps=2.090e+07
2023-07-07 14:26:01,065 -        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 14:26:09,065 -        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 14:26:17,064 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2000, best=0.53, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 14:26:25,097 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2100, best=0.52, avg=0.50, std=0.01, steps=2.582e+07
2023-07-07 14:26:33,117 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.01, steps=2.705e+07
2023-07-07 14:26:41,121 -        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 14:26:49,111 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 2400, best=0.53, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 14:26:57,119 -        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 14:27:05,127 -        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 14:27:13,138 -        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 14:27:21,139 -        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 14:27:29,141 -        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 14:27:37,138 -        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 14:27:45,138 -        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 14:27:53,147 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 14:28:01,150 -        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 14:28:09,143 -        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 14:28:17,156 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3500, best=0.53, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 14:28:25,155 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 14:28:33,157 -        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 14:28:41,164 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 3800, best=0.52, avg=0.50, std=0.01, steps=4.671e+07
2023-07-07 14:28:49,185 -        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 14:28:57,198 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4000, best=0.53, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:29:05,223 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 14:29:13,226 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:29:21,245 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 14:29:29,261 -        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 14:29:37,280 -        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 14:29:45,293 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 4600, best=0.53, avg=0.50, std=0.01, steps=5.654e+07
2023-07-07 14:29:53,291 -        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 14:30:01,288 -        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 14:30:09,271 -        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 14:30:17,260 -        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 14:30:25,257 -        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 14:30:33,278 -        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 14:30:41,289 -        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 14:30:49,305 -        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 14:30:57,337 -        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 14:31:05,381 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 14:31:13,408 -        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 14:31:21,421 -        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 14:31:29,435 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 5900, best=0.53, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 14:31:37,460 -        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 14:31:45,471 -        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 14:31:53,471 -        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 14:32:01,475 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6300, best=0.53, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 14:32:09,484 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.01, steps=7.866e+07
2023-07-07 14:32:17,495 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6500, best=0.53, avg=0.50, std=0.01, steps=7.988e+07
2023-07-07 14:32:25,504 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6600, best=0.53, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 14:32:33,521 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 14:32:41,523 -        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 14:32:49,529 -        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 14:32:57,555 -        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 14:33:05,573 -        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 14:33:13,590 -        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 14:33:21,600 -        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 14:33:29,612 -        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 14:33:37,621 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7500, best=0.53, avg=0.50, std=0.01, steps=9.217e+07
2023-07-07 14:33:45,626 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 7600, best=0.53, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 14:33:53,638 -        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 14:34:01,647 -        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 14:34:09,689 -        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 14:34:17,682 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8000, best=0.52, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 14:34:25,670 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 14:34:33,664 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 14:34:41,667 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 14:34:49,673 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8400, best=0.53, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 14:34:57,681 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8500, best=0.52, avg=0.50, std=0.01, steps=1.045e+08
2023-07-07 14:35:05,704 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8600, best=0.52, avg=0.50, std=0.01, steps=1.057e+08
2023-07-07 14:35:13,708 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.069e+08
2023-07-07 14:35:21,727 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 14:35:29,737 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=1.094e+08
2023-07-07 14:35:37,750 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9000, best=0.52, avg=0.50, std=0.01, steps=1.106e+08
2023-07-07 14:35:45,776 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9100, best=0.53, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 14:35:53,796 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9200, best=0.52, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 14:36:01,799 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=1.143e+08
2023-07-07 14:36:09,800 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=1.155e+08
2023-07-07 14:36:17,804 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9500, best=0.52, avg=0.50, std=0.01, steps=1.167e+08
2023-07-07 14:36:25,814 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9600, best=0.52, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 14:36:33,827 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9700, best=0.52, avg=0.50, std=0.01, steps=1.192e+08
2023-07-07 14:36:41,854 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 14:36:49,874 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=1.217e+08
2023-07-07 14:36:57,902 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10000, best=0.52, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 14:37:05,920 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 14:37:13,932 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.253e+08
2023-07-07 14:37:21,953 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10300, best=0.52, avg=0.50, std=0.01, steps=1.266e+08
2023-07-07 14:37:29,980 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 14:37:38,016 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.290e+08
2023-07-07 14:37:46,031 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10600, best=0.53, avg=0.50, std=0.01, steps=1.303e+08
2023-07-07 14:37:54,061 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10700, best=0.53, avg=0.50, std=0.01, steps=1.315e+08
2023-07-07 14:38:02,071 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10800, best=0.52, avg=0.50, std=0.01, steps=1.327e+08
2023-07-07 14:38:10,070 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 10900, best=0.52, avg=0.50, std=0.01, steps=1.340e+08
2023-07-07 14:38:18,066 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11000, best=0.52, avg=0.50, std=0.01, steps=1.352e+08
2023-07-07 14:38:26,069 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.01, steps=1.364e+08
2023-07-07 14:38:34,078 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.01, steps=1.376e+08
2023-07-07 14:38:42,085 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11300, best=0.52, avg=0.50, std=0.01, steps=1.389e+08
2023-07-07 14:38:50,090 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11400, best=0.52, avg=0.50, std=0.01, steps=1.401e+08
2023-07-07 14:38:58,095 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11500, best=0.52, avg=0.50, std=0.01, steps=1.413e+08
2023-07-07 14:39:06,141 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11600, best=0.52, avg=0.50, std=0.01, steps=1.426e+08
2023-07-07 14:39:14,168 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11700, best=0.52, avg=0.50, std=0.01, steps=1.438e+08
2023-07-07 14:39:22,181 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11800, best=0.52, avg=0.50, std=0.01, steps=1.450e+08
2023-07-07 14:39:30,188 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11900, best=0.52, avg=0.50, std=0.01, steps=1.462e+08
2023-07-07 14:39:38,118 -        meta learning: [    INFO] - [Len Lat Rep]: 8, 32, 0, [Train]: 11999, best=0.52, avg=0.50, std=0.01, steps=1.475e+08
2023-07-07 14:39:38,119 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 14:39:38,143 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:39:38,143 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:39:38,174 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:39:45,148 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=8.274e+05
2023-07-07 14:39:50,592 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 200, best=0.52, avg=0.50, std=0.01, steps=1.647e+06
2023-07-07 14:39:56,022 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=2.466e+06
2023-07-07 14:40:01,453 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=3.285e+06
2023-07-07 14:40:06,887 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.01, steps=4.104e+06
2023-07-07 14:40:12,325 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=4.923e+06
2023-07-07 14:40:17,755 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 700, best=0.52, avg=0.50, std=0.01, steps=5.743e+06
2023-07-07 14:40:23,188 -        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 14:40:28,615 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=7.381e+06
2023-07-07 14:40:34,043 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.00, steps=8.200e+06
2023-07-07 14:40:39,484 -        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 14:40:44,930 -        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 14:40:50,370 -        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 14:40:55,821 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=1.148e+07
2023-07-07 14:41:01,256 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1500, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:41:06,692 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.01, steps=1.312e+07
2023-07-07 14:41:12,161 -        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 14:41:17,611 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.01, steps=1.475e+07
2023-07-07 14:41:23,049 -        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 14:41:28,479 -        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 14:41:33,902 -        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 14:41:39,336 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2200, best=0.52, avg=0.50, std=0.01, steps=1.803e+07
2023-07-07 14:41:44,785 -        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 14:41:50,223 -        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 14:41:55,647 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.01, steps=2.049e+07
2023-07-07 14:42:01,079 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=2.131e+07
2023-07-07 14:42:06,505 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.213e+07
2023-07-07 14:42:11,943 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 14:42:17,370 -        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 14:42:22,802 -        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 14:42:28,240 -        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 14:42:33,690 -        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 14:42:39,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.00, steps=2.704e+07
2023-07-07 14:42:44,568 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.01, steps=2.786e+07
2023-07-07 14:42:50,005 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 14:42:55,444 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 3600, best=0.52, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 14:43:00,883 -        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 14:43:06,334 -        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 14:43:11,776 -        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 14:43:17,213 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:43:22,643 -        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 14:43:28,076 -        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 14:43:33,509 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=3.523e+07
2023-07-07 14:43:38,973 -        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 14:43:44,430 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4500, best=0.52, avg=0.50, std=0.01, steps=3.687e+07
2023-07-07 14:43:49,866 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 4600, best=0.52, avg=0.50, std=0.01, steps=3.769e+07
2023-07-07 14:43:55,303 -        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 14:44:00,735 -        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 14:44:06,180 -        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 14:44:11,622 -        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 14:44:17,061 -        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 14:44:22,503 -        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 14:44:27,940 -        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 14:44:33,382 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5400, best=0.52, avg=0.50, std=0.01, steps=4.424e+07
2023-07-07 14:44:38,820 -        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 14:44:44,266 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5600, best=0.52, avg=0.50, std=0.01, steps=4.588e+07
2023-07-07 14:44:49,707 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=4.670e+07
2023-07-07 14:44:55,134 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=4.752e+07
2023-07-07 14:45:00,574 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 5900, best=0.52, avg=0.50, std=0.01, steps=4.834e+07
2023-07-07 14:45:06,015 -        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 14:45:11,460 -        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 14:45:16,901 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=5.080e+07
2023-07-07 14:45:22,345 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=5.162e+07
2023-07-07 14:45:27,783 -        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 14:45:33,224 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=5.326e+07
2023-07-07 14:45:38,657 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 14:45:44,102 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=5.489e+07
2023-07-07 14:45:49,535 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6800, best=0.52, avg=0.50, std=0.01, steps=5.571e+07
2023-07-07 14:45:54,959 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=5.653e+07
2023-07-07 14:46:00,398 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=5.735e+07
2023-07-07 14:46:05,831 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=5.817e+07
2023-07-07 14:46:11,269 -        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 14:46:16,699 -        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 14:46:22,130 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=6.063e+07
2023-07-07 14:46:27,566 -        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 14:46:32,997 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=6.227e+07
2023-07-07 14:46:38,438 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.01, steps=6.309e+07
2023-07-07 14:46:43,884 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7800, best=0.52, avg=0.50, std=0.01, steps=6.391e+07
2023-07-07 14:46:49,328 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.01, steps=6.472e+07
2023-07-07 14:46:54,761 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.01, steps=6.554e+07
2023-07-07 14:47:00,198 -        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 14:47:05,638 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=6.718e+07
2023-07-07 14:47:11,070 -        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 14:47:16,506 -        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 14:47:21,946 -        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 14:47:27,382 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.01, steps=7.046e+07
2023-07-07 14:47:32,816 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.00, steps=7.128e+07
2023-07-07 14:47:38,252 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 8800, best=0.52, avg=0.50, std=0.01, steps=7.210e+07
2023-07-07 14:47:43,688 -        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 14:47:49,121 -        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 14:47:54,556 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9100, best=0.52, avg=0.50, std=0.01, steps=7.456e+07
2023-07-07 14:47:59,975 -        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 14:48:05,407 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9300, best=0.52, avg=0.50, std=0.01, steps=7.619e+07
2023-07-07 14:48:10,839 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9400, best=0.52, avg=0.50, std=0.01, steps=7.701e+07
2023-07-07 14:48:16,271 -        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 14:48:21,697 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.01, steps=7.865e+07
2023-07-07 14:48:27,133 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9700, best=0.52, avg=0.50, std=0.00, steps=7.947e+07
2023-07-07 14:48:32,572 -        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 14:48:38,006 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 14:48:43,438 -        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 14:48:48,875 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10100, best=0.52, avg=0.50, std=0.01, steps=8.275e+07
2023-07-07 14:48:54,313 -        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 14:48:59,747 -        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 14:49:05,182 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.01, steps=8.520e+07
2023-07-07 14:49:10,617 -        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 14:49:16,058 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10600, best=0.52, avg=0.50, std=0.01, steps=8.684e+07
2023-07-07 14:49:21,486 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10700, best=0.52, avg=0.50, std=0.01, steps=8.766e+07
2023-07-07 14:49:26,918 -        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 14:49:32,349 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.01, steps=8.930e+07
2023-07-07 14:49:37,793 -        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 14:49:43,223 -        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 14:49:48,651 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.00, steps=9.176e+07
2023-07-07 14:49:54,088 -        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 14:49:59,540 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 14:50:04,982 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11500, best=0.52, avg=0.50, std=0.01, steps=9.422e+07
2023-07-07 14:50:10,413 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.01, steps=9.504e+07
2023-07-07 14:50:15,845 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.01, steps=9.585e+07
2023-07-07 14:50:21,290 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.01, steps=9.667e+07
2023-07-07 14:50:26,734 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.01, steps=9.749e+07
2023-07-07 14:50:32,128 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 0, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.01, steps=9.830e+07
2023-07-07 14:50:32,128 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 14:50:32,153 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 14:50:32,153 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 14:50:32,184 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 14:50:40,467 -        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 14:50:47,181 -        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 14:50:53,906 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 300, best=0.52, avg=0.50, std=0.01, steps=3.082e+06
2023-07-07 14:51:00,631 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.106e+06
2023-07-07 14:51:07,334 -        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 14:51:14,043 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=6.154e+06
2023-07-07 14:51:20,766 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=7.178e+06
2023-07-07 14:51:27,495 -        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 14:51:34,217 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 900, best=0.52, avg=0.50, std=0.01, steps=9.226e+06
2023-07-07 14:51:40,930 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.025e+07
2023-07-07 14:51:47,646 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.127e+07
2023-07-07 14:51:54,358 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1200, best=0.52, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 14:52:01,056 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1300, best=0.51, avg=0.50, std=0.01, steps=1.332e+07
2023-07-07 14:52:07,770 -        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 14:52:14,481 -        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 14:52:21,195 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=1.639e+07
2023-07-07 14:52:27,933 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1700, best=0.51, avg=0.50, std=0.01, steps=1.742e+07
2023-07-07 14:52:34,644 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1800, best=0.52, avg=0.50, std=0.01, steps=1.844e+07
2023-07-07 14:52:41,364 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=1.947e+07
2023-07-07 14:52:48,098 -        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 14:52:54,814 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.01, steps=2.151e+07
2023-07-07 14:53:01,528 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.00, steps=2.254e+07
2023-07-07 14:53:08,241 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2300, best=0.52, avg=0.50, std=0.01, steps=2.356e+07
2023-07-07 14:53:14,949 -        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 14:53:21,667 -        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 14:53:28,382 -        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 14:53:35,112 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=2.766e+07
2023-07-07 14:53:41,825 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=2.868e+07
2023-07-07 14:53:48,540 -        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 14:53:55,251 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3000, best=0.52, avg=0.50, std=0.01, steps=3.073e+07
2023-07-07 14:54:01,978 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.01, steps=3.175e+07
2023-07-07 14:54:08,713 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3200, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 14:54:15,441 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3300, best=0.51, avg=0.50, std=0.01, steps=3.380e+07
2023-07-07 14:54:22,163 -        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 14:54:28,879 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.01, steps=3.585e+07
2023-07-07 14:54:35,607 -        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 14:54:42,319 -        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 14:54:49,044 -        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 14:54:55,775 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.01, steps=3.995e+07
2023-07-07 14:55:02,487 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=4.097e+07
2023-07-07 14:55:09,194 -        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 14:55:15,907 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4200, best=0.51, avg=0.50, std=0.00, steps=4.302e+07
2023-07-07 14:55:22,623 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4300, best=0.52, avg=0.50, std=0.01, steps=4.404e+07
2023-07-07 14:55:29,331 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4400, best=0.52, avg=0.50, std=0.01, steps=4.507e+07
2023-07-07 14:55:36,041 -        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 14:55:42,757 -        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 14:55:49,466 -        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 14:55:56,185 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4800, best=0.52, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 14:56:02,927 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 4900, best=0.52, avg=0.50, std=0.01, steps=5.019e+07
2023-07-07 14:56:09,641 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5000, best=0.51, avg=0.50, std=0.01, steps=5.121e+07
2023-07-07 14:56:16,355 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5100, best=0.52, avg=0.50, std=0.01, steps=5.223e+07
2023-07-07 14:56:23,072 -        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 14:56:29,790 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.01, steps=5.428e+07
2023-07-07 14:56:36,509 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=5.531e+07
2023-07-07 14:56:43,215 -        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 14:56:49,928 -        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 14:56:56,638 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.01, steps=5.838e+07
2023-07-07 14:57:03,360 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.01, steps=5.940e+07
2023-07-07 14:57:10,067 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=6.043e+07
2023-07-07 14:57:16,785 -        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 14:57:23,492 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.01, steps=6.247e+07
2023-07-07 14:57:30,190 -        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 14:57:36,896 -        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 14:57:43,602 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6400, best=0.51, avg=0.50, std=0.00, steps=6.555e+07
2023-07-07 14:57:50,319 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.01, steps=6.657e+07
2023-07-07 14:57:57,035 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=6.759e+07
2023-07-07 14:58:03,761 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=6.862e+07
2023-07-07 14:58:10,502 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=6.964e+07
2023-07-07 14:58:17,221 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=7.067e+07
2023-07-07 14:58:23,955 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.01, steps=7.169e+07
2023-07-07 14:58:30,657 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=7.271e+07
2023-07-07 14:58:37,377 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.01, steps=7.374e+07
2023-07-07 14:58:44,094 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=7.476e+07
2023-07-07 14:58:50,833 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=7.579e+07
2023-07-07 14:58:57,542 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7500, best=0.52, avg=0.50, std=0.01, steps=7.681e+07
2023-07-07 14:59:04,261 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=7.783e+07
2023-07-07 14:59:10,969 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7700, best=0.52, avg=0.50, std=0.01, steps=7.886e+07
2023-07-07 14:59:17,679 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7800, best=0.65, avg=0.64, std=0.00, steps=7.988e+07
2023-07-07 14:59:24,387 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 7900, best=0.68, avg=0.67, std=0.00, steps=8.091e+07
2023-07-07 14:59:31,092 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8000, best=0.70, avg=0.69, std=0.00, steps=8.193e+07
2023-07-07 14:59:37,795 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8100, best=0.71, avg=0.70, std=0.00, steps=8.295e+07
2023-07-07 14:59:44,502 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8200, best=0.71, avg=0.70, std=0.00, steps=8.398e+07
2023-07-07 14:59:51,210 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8300, best=0.72, avg=0.71, std=0.00, steps=8.500e+07
2023-07-07 14:59:57,925 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8400, best=0.73, avg=0.71, std=0.00, steps=8.603e+07
2023-07-07 15:00:04,652 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8500, best=0.73, avg=0.72, std=0.00, steps=8.705e+07
2023-07-07 15:00:11,361 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8600, best=0.73, avg=0.72, std=0.00, steps=8.807e+07
2023-07-07 15:00:18,067 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8700, best=0.74, avg=0.73, std=0.00, steps=8.910e+07
2023-07-07 15:00:24,775 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8800, best=0.74, avg=0.73, std=0.00, steps=9.012e+07
2023-07-07 15:00:31,487 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 8900, best=0.75, avg=0.74, std=0.00, steps=9.115e+07
2023-07-07 15:00:38,194 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9000, best=0.76, avg=0.75, std=0.00, steps=9.217e+07
2023-07-07 15:00:44,903 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9100, best=0.76, avg=0.75, std=0.00, steps=9.319e+07
2023-07-07 15:00:51,620 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9200, best=0.76, avg=0.75, std=0.00, steps=9.422e+07
2023-07-07 15:00:58,340 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9300, best=0.77, avg=0.76, std=0.00, steps=9.524e+07
2023-07-07 15:01:05,069 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9400, best=0.77, avg=0.76, std=0.00, steps=9.627e+07
2023-07-07 15:01:11,785 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9500, best=0.78, avg=0.77, std=0.00, steps=9.729e+07
2023-07-07 15:01:18,499 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9600, best=0.78, avg=0.77, std=0.00, steps=9.831e+07
2023-07-07 15:01:25,217 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9700, best=0.79, avg=0.77, std=0.00, steps=9.934e+07
2023-07-07 15:01:31,930 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9800, best=0.79, avg=0.78, std=0.00, steps=1.004e+08
2023-07-07 15:01:38,637 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 9900, best=0.79, avg=0.78, std=0.00, steps=1.014e+08
2023-07-07 15:01:45,341 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10000, best=0.79, avg=0.78, std=0.00, steps=1.024e+08
2023-07-07 15:01:52,057 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10100, best=0.79, avg=0.79, std=0.00, steps=1.034e+08
2023-07-07 15:01:58,760 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10200, best=0.80, avg=0.79, std=0.00, steps=1.045e+08
2023-07-07 15:02:05,466 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10300, best=0.80, avg=0.79, std=0.00, steps=1.055e+08
2023-07-07 15:02:12,174 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10400, best=0.80, avg=0.79, std=0.00, steps=1.065e+08
2023-07-07 15:02:18,886 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10500, best=0.81, avg=0.79, std=0.00, steps=1.075e+08
2023-07-07 15:02:25,605 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10600, best=0.80, avg=0.80, std=0.00, steps=1.086e+08
2023-07-07 15:02:32,315 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10700, best=0.80, avg=0.80, std=0.00, steps=1.096e+08
2023-07-07 15:02:39,014 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10800, best=0.81, avg=0.80, std=0.00, steps=1.106e+08
2023-07-07 15:02:45,727 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 10900, best=0.81, avg=0.80, std=0.00, steps=1.116e+08
2023-07-07 15:02:52,463 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11000, best=0.81, avg=0.80, std=0.00, steps=1.127e+08
2023-07-07 15:02:59,188 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11100, best=0.82, avg=0.81, std=0.00, steps=1.137e+08
2023-07-07 15:03:05,893 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11200, best=0.82, avg=0.81, std=0.00, steps=1.147e+08
2023-07-07 15:03:12,611 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11300, best=0.82, avg=0.81, std=0.00, steps=1.157e+08
2023-07-07 15:03:19,325 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11400, best=0.82, avg=0.81, std=0.00, steps=1.167e+08
2023-07-07 15:03:26,035 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11500, best=0.82, avg=0.81, std=0.00, steps=1.178e+08
2023-07-07 15:03:32,763 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11600, best=0.82, avg=0.81, std=0.00, steps=1.188e+08
2023-07-07 15:03:39,479 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11700, best=0.83, avg=0.82, std=0.00, steps=1.198e+08
2023-07-07 15:03:46,185 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11800, best=0.83, avg=0.82, std=0.00, steps=1.208e+08
2023-07-07 15:03:52,905 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11900, best=0.83, avg=0.82, std=0.00, steps=1.219e+08
2023-07-07 15:03:59,551 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 8, 0, [Train]: 11999, best=0.83, avg=0.82, std=0.00, steps=1.229e+08
2023-07-07 15:03:59,552 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 15:03:59,577 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:03:59,577 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:03:59,610 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:04:09,190 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 100, best=0.51, avg=0.50, std=0.01, steps=1.241e+06
2023-07-07 15:04:17,192 -        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 15:04:25,193 -        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 15:04:33,214 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 400, best=0.51, avg=0.50, std=0.01, steps=4.927e+06
2023-07-07 15:04:41,218 -        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 15:04:49,243 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 600, best=0.52, avg=0.50, std=0.01, steps=7.385e+06
2023-07-07 15:04:57,273 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=8.614e+06
2023-07-07 15:05:05,290 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 800, best=0.51, avg=0.50, std=0.01, steps=9.843e+06
2023-07-07 15:05:13,308 -        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 15:05:21,323 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.230e+07
2023-07-07 15:05:29,328 -        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 15:05:37,336 -        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 15:05:45,324 -        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 15:05:53,318 -        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 15:06:01,317 -        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 15:06:09,326 -        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 15:06:17,338 -        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 15:06:25,339 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=2.213e+07
2023-07-07 15:06:33,339 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=2.336e+07
2023-07-07 15:06:41,328 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2000, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 15:06:49,341 -        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 15:06:57,353 -        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 15:07:05,381 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2300, best=0.51, avg=0.50, std=0.01, steps=2.827e+07
2023-07-07 15:07:13,403 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.01, steps=2.950e+07
2023-07-07 15:07:21,419 -        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 15:07:29,449 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2600, best=0.52, avg=0.50, std=0.01, steps=3.196e+07
2023-07-07 15:07:37,459 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2700, best=0.51, avg=0.50, std=0.01, steps=3.319e+07
2023-07-07 15:07:45,457 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2800, best=0.52, avg=0.50, std=0.01, steps=3.442e+07
2023-07-07 15:07:53,454 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=3.565e+07
2023-07-07 15:08:01,451 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.01, steps=3.688e+07
2023-07-07 15:08:09,446 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=3.811e+07
2023-07-07 15:08:17,446 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.01, steps=3.933e+07
2023-07-07 15:08:25,461 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=4.056e+07
2023-07-07 15:08:33,484 -        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 15:08:41,492 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3500, best=0.52, avg=0.50, std=0.01, steps=4.302e+07
2023-07-07 15:08:49,498 -        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 15:08:57,511 -        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 15:09:05,520 -        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 15:09:13,520 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 3900, best=0.52, avg=0.50, std=0.01, steps=4.794e+07
2023-07-07 15:09:21,528 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4000, best=0.51, avg=0.50, std=0.01, steps=4.916e+07
2023-07-07 15:09:29,548 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4100, best=0.51, avg=0.50, std=0.01, steps=5.039e+07
2023-07-07 15:09:37,560 -        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 15:09:45,569 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=5.285e+07
2023-07-07 15:09:53,557 -        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 15:10:01,553 -        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 15:10:09,561 -        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 15:10:17,556 -        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 15:10:25,562 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=5.899e+07
2023-07-07 15:10:33,579 -        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 15:10:41,593 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5000, best=0.52, avg=0.50, std=0.01, steps=6.145e+07
2023-07-07 15:10:49,583 -        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 15:10:57,594 -        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 15:11:05,624 -        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 15:11:13,670 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.01, steps=6.637e+07
2023-07-07 15:11:21,718 -        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 15:11:29,732 -        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 15:11:37,728 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=7.005e+07
2023-07-07 15:11:45,759 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5800, best=0.52, avg=0.50, std=0.01, steps=7.128e+07
2023-07-07 15:11:53,784 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=7.251e+07
2023-07-07 15:12:01,795 -        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 15:12:09,808 -        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 15:12:17,819 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6200, best=0.52, avg=0.50, std=0.01, steps=7.620e+07
2023-07-07 15:12:25,812 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6300, best=0.52, avg=0.50, std=0.01, steps=7.743e+07
2023-07-07 15:12:33,808 -        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 15:12:41,847 -        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 15:12:49,860 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=8.111e+07
2023-07-07 15:12:57,857 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6700, best=0.52, avg=0.50, std=0.01, steps=8.234e+07
2023-07-07 15:13:05,851 -        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 15:13:13,858 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=8.480e+07
2023-07-07 15:13:21,856 -        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 15:13:29,881 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7100, best=0.52, avg=0.50, std=0.01, steps=8.726e+07
2023-07-07 15:13:37,891 -        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 15:13:45,902 -        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 15:13:53,925 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.01, steps=9.094e+07
2023-07-07 15:14:01,957 -        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 15:14:09,982 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.01, steps=9.340e+07
2023-07-07 15:14:17,992 -        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 15:14:25,987 -        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 15:14:33,999 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 7900, best=0.52, avg=0.50, std=0.01, steps=9.709e+07
2023-07-07 15:14:41,999 -        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 15:14:49,992 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=9.955e+07
2023-07-07 15:14:57,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8200, best=0.52, avg=0.50, std=0.01, steps=1.008e+08
2023-07-07 15:15:05,989 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.020e+08
2023-07-07 15:15:13,997 -        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 15:15:22,013 -        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 15:15:30,043 -        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 15:15:38,056 -        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 15:15:46,063 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.01, steps=1.081e+08
2023-07-07 15:15:54,073 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.094e+08
2023-07-07 15:16:02,079 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.01, steps=1.106e+08
2023-07-07 15:16:10,083 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.01, steps=1.118e+08
2023-07-07 15:16:18,079 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 15:16:26,071 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.01, steps=1.143e+08
2023-07-07 15:16:34,060 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.01, steps=1.155e+08
2023-07-07 15:16:42,065 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.01, steps=1.167e+08
2023-07-07 15:16:50,088 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.01, steps=1.180e+08
2023-07-07 15:16:58,091 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.01, steps=1.192e+08
2023-07-07 15:17:06,105 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9800, best=0.52, avg=0.50, std=0.01, steps=1.204e+08
2023-07-07 15:17:14,106 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=1.217e+08
2023-07-07 15:17:22,116 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.01, steps=1.229e+08
2023-07-07 15:17:30,140 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.01, steps=1.241e+08
2023-07-07 15:17:38,156 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10200, best=0.52, avg=0.50, std=0.01, steps=1.253e+08
2023-07-07 15:17:46,161 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=1.266e+08
2023-07-07 15:17:54,180 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10400, best=0.52, avg=0.50, std=0.01, steps=1.278e+08
2023-07-07 15:18:02,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.290e+08
2023-07-07 15:18:10,165 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.01, steps=1.303e+08
2023-07-07 15:18:18,167 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.01, steps=1.315e+08
2023-07-07 15:18:26,170 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10800, best=0.64, avg=0.63, std=0.00, steps=1.327e+08
2023-07-07 15:18:34,171 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 10900, best=0.66, avg=0.65, std=0.00, steps=1.340e+08
2023-07-07 15:18:42,177 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11000, best=0.66, avg=0.65, std=0.00, steps=1.352e+08
2023-07-07 15:18:50,188 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11100, best=0.67, avg=0.66, std=0.00, steps=1.364e+08
2023-07-07 15:18:58,232 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11200, best=0.68, avg=0.67, std=0.00, steps=1.376e+08
2023-07-07 15:19:06,267 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11300, best=0.69, avg=0.68, std=0.00, steps=1.389e+08
2023-07-07 15:19:14,277 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11400, best=0.70, avg=0.69, std=0.00, steps=1.401e+08
2023-07-07 15:19:22,288 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11500, best=0.70, avg=0.69, std=0.00, steps=1.413e+08
2023-07-07 15:19:30,293 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11600, best=0.71, avg=0.70, std=0.00, steps=1.426e+08
2023-07-07 15:19:38,295 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11700, best=0.71, avg=0.70, std=0.00, steps=1.438e+08
2023-07-07 15:19:46,315 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11800, best=0.72, avg=0.71, std=0.00, steps=1.450e+08
2023-07-07 15:19:54,321 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11900, best=0.72, avg=0.71, std=0.00, steps=1.462e+08
2023-07-07 15:20:02,264 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 16, 0, [Train]: 11999, best=0.73, avg=0.71, std=0.00, steps=1.475e+08
2023-07-07 15:20:02,266 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 15:20:02,291 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:20:02,291 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:20:02,323 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:20:14,635 -        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 15:20:25,279 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 200, best=0.51, avg=0.50, std=0.01, steps=3.293e+06
2023-07-07 15:20:35,890 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=4.932e+06
2023-07-07 15:20:46,503 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 400, best=0.52, avg=0.50, std=0.00, steps=6.570e+06
2023-07-07 15:20:57,139 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 500, best=0.52, avg=0.50, std=0.01, steps=8.208e+06
2023-07-07 15:21:07,796 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 600, best=0.51, avg=0.50, std=0.01, steps=9.847e+06
2023-07-07 15:21:18,422 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 700, best=0.51, avg=0.50, std=0.01, steps=1.149e+07
2023-07-07 15:21:29,046 -        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 15:21:39,667 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 900, best=0.51, avg=0.50, std=0.01, steps=1.476e+07
2023-07-07 15:21:50,286 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1000, best=0.51, avg=0.50, std=0.01, steps=1.640e+07
2023-07-07 15:22:00,903 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1100, best=0.52, avg=0.50, std=0.01, steps=1.804e+07
2023-07-07 15:22:11,514 -        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 15:22:22,155 -        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 15:22:32,768 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1400, best=0.52, avg=0.50, std=0.01, steps=2.295e+07
2023-07-07 15:22:43,407 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1500, best=0.51, avg=0.50, std=0.01, steps=2.459e+07
2023-07-07 15:22:54,084 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 15:23:04,743 -        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 15:23:15,352 -        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 15:23:25,973 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 1900, best=0.52, avg=0.50, std=0.01, steps=3.115e+07
2023-07-07 15:23:36,579 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2000, best=0.52, avg=0.50, std=0.01, steps=3.278e+07
2023-07-07 15:23:47,178 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2100, best=0.51, avg=0.50, std=0.00, steps=3.442e+07
2023-07-07 15:23:57,793 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2200, best=0.51, avg=0.50, std=0.01, steps=3.606e+07
2023-07-07 15:24:08,439 -        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 15:24:19,062 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2400, best=0.52, avg=0.50, std=0.01, steps=3.934e+07
2023-07-07 15:24:29,694 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2500, best=0.52, avg=0.50, std=0.01, steps=4.098e+07
2023-07-07 15:24:40,302 -        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 15:24:50,922 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2700, best=0.52, avg=0.50, std=0.01, steps=4.425e+07
2023-07-07 15:25:01,536 -        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 15:25:12,155 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 2900, best=0.51, avg=0.50, std=0.01, steps=4.753e+07
2023-07-07 15:25:22,773 -        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 15:25:33,406 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3100, best=0.52, avg=0.50, std=0.01, steps=5.081e+07
2023-07-07 15:25:44,028 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.01, steps=5.245e+07
2023-07-07 15:25:54,633 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3300, best=0.52, avg=0.50, std=0.01, steps=5.408e+07
2023-07-07 15:26:05,250 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=5.572e+07
2023-07-07 15:26:15,876 -        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 15:26:26,517 -        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 15:26:37,139 -        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 15:26:47,768 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.01, steps=6.228e+07
2023-07-07 15:26:58,374 -        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 15:27:08,990 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4000, best=0.52, avg=0.50, std=0.01, steps=6.555e+07
2023-07-07 15:27:19,617 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4100, best=0.52, avg=0.50, std=0.01, steps=6.719e+07
2023-07-07 15:27:30,239 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4200, best=0.52, avg=0.50, std=0.01, steps=6.883e+07
2023-07-07 15:27:40,875 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.01, steps=7.047e+07
2023-07-07 15:27:51,493 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=7.211e+07
2023-07-07 15:28:02,125 -        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 15:28:12,756 -        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 15:28:23,380 -        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 15:28:34,022 -        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 15:28:44,664 -        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 15:28:55,270 -        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 15:29:05,876 -        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 15:29:16,494 -        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 15:29:27,132 -        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 15:29:37,753 -        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 15:29:48,377 -        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 15:29:58,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5600, best=0.51, avg=0.50, std=0.01, steps=9.177e+07
2023-07-07 15:30:09,615 -        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 15:30:20,281 -        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 15:30:30,912 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 5900, best=0.51, avg=0.50, std=0.01, steps=9.668e+07
2023-07-07 15:30:41,534 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6000, best=0.51, avg=0.50, std=0.01, steps=9.832e+07
2023-07-07 15:30:52,169 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6100, best=0.51, avg=0.50, std=0.01, steps=9.996e+07
2023-07-07 15:31:02,788 -        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 15:31:13,417 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6300, best=0.51, avg=0.50, std=0.01, steps=1.032e+08
2023-07-07 15:31:24,033 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6400, best=0.52, avg=0.50, std=0.01, steps=1.049e+08
2023-07-07 15:31:34,639 -        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 15:31:45,247 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.01, steps=1.082e+08
2023-07-07 15:31:55,850 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6700, best=0.51, avg=0.50, std=0.01, steps=1.098e+08
2023-07-07 15:32:06,466 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.01, steps=1.114e+08
2023-07-07 15:32:17,060 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.01, steps=1.131e+08
2023-07-07 15:32:27,669 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7000, best=0.52, avg=0.50, std=0.01, steps=1.147e+08
2023-07-07 15:32:38,276 -        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 15:32:48,887 -        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 15:32:59,483 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.01, steps=1.196e+08
2023-07-07 15:33:10,098 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7400, best=0.52, avg=0.50, std=0.01, steps=1.213e+08
2023-07-07 15:33:20,706 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=1.229e+08
2023-07-07 15:33:31,329 -        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 15:33:41,962 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.01, steps=1.262e+08
2023-07-07 15:33:52,566 -        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 15:34:03,166 -        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 15:34:13,775 -        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 15:34:24,375 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8100, best=0.52, avg=0.50, std=0.01, steps=1.327e+08
2023-07-07 15:34:34,991 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=1.344e+08
2023-07-07 15:34:45,584 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8300, best=0.52, avg=0.50, std=0.01, steps=1.360e+08
2023-07-07 15:34:56,185 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.01, steps=1.376e+08
2023-07-07 15:35:06,778 -        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 15:35:17,382 -        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 15:35:27,978 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.01, steps=1.426e+08
2023-07-07 15:35:38,570 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.01, steps=1.442e+08
2023-07-07 15:35:49,173 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 8900, best=0.52, avg=0.50, std=0.01, steps=1.458e+08
2023-07-07 15:35:59,793 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.01, steps=1.475e+08
2023-07-07 15:36:10,387 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.491e+08
2023-07-07 15:36:20,998 -        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 15:36:31,587 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.01, steps=1.524e+08
2023-07-07 15:36:42,183 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.01, steps=1.540e+08
2023-07-07 15:36:52,834 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.01, steps=1.557e+08
2023-07-07 15:37:03,433 -        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 15:37:14,034 -        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 15:37:24,631 -        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 15:37:35,228 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 9900, best=0.52, avg=0.50, std=0.01, steps=1.622e+08
2023-07-07 15:37:45,829 -        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 15:37:56,428 -        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 15:38:07,054 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.01, steps=1.671e+08
2023-07-07 15:38:17,676 -        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 15:38:28,295 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=1.704e+08
2023-07-07 15:38:38,905 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10500, best=0.52, avg=0.50, std=0.01, steps=1.720e+08
2023-07-07 15:38:49,531 -        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 15:39:00,149 -        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 15:39:10,771 -        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 15:39:21,398 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.01, steps=1.786e+08
2023-07-07 15:39:32,035 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.01, steps=1.802e+08
2023-07-07 15:39:42,639 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11100, best=0.52, avg=0.50, std=0.01, steps=1.819e+08
2023-07-07 15:39:53,242 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11200, best=0.52, avg=0.50, std=0.01, steps=1.835e+08
2023-07-07 15:40:03,854 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11300, best=0.52, avg=0.50, std=0.01, steps=1.852e+08
2023-07-07 15:40:14,447 -        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 15:40:25,048 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=1.884e+08
2023-07-07 15:40:35,644 -        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 15:40:46,270 -        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 15:40:56,871 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.01, steps=1.933e+08
2023-07-07 15:41:07,476 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11900, best=0.52, avg=0.50, std=0.01, steps=1.950e+08
2023-07-07 15:41:17,984 -        meta learning: [    INFO] - [Len Lat Rep]: 16, 32, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=1.966e+08
2023-07-07 15:41:17,985 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 15:41:18,010 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 15:41:18,010 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 15:41:18,043 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 15:41:30,482 -        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 15:41:41,064 -        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 15:41:51,641 -        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 15:42:02,207 -        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 15:42:12,769 -        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 15:42:23,353 -        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 15:42:33,936 -        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 15:42:44,510 -        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 15:42:55,100 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=1.476e+07
2023-07-07 15:43:05,687 -        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 15:43:16,255 -        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 15:43:26,823 -        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 15:43:37,394 -        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 15:43:47,954 -        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 15:43:58,520 -        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 15:44:09,096 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 1600, best=0.51, avg=0.50, std=0.00, steps=2.623e+07
2023-07-07 15:44:19,675 -        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 15:44:30,258 -        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 15:44:40,830 -        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 15:44:51,411 -        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 15:45:01,994 -        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 15:45:12,567 -        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 15:45:23,134 -        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 15:45:33,699 -        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 15:45:44,263 -        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 15:45:54,830 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=4.261e+07
2023-07-07 15:46:05,401 -        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 15:46:15,998 -        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 15:46:26,576 -        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 15:46:37,132 -        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 15:46:47,710 -        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 15:46:58,300 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=5.245e+07
2023-07-07 15:47:08,863 -        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 15:47:19,423 -        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 15:47:29,989 -        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 15:47:40,567 -        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 15:47:51,151 -        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 15:48:01,709 -        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 15:48:12,287 -        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 15:48:22,846 -        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 15:48:33,415 -        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 15:48:44,001 -        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 15:48:54,575 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 4300, best=0.51, avg=0.50, std=0.00, steps=7.047e+07
2023-07-07 15:49:05,148 -        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 15:49:15,697 -        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 15:49:26,262 -        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 15:49:36,857 -        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 15:49:47,420 -        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 15:49:57,989 -        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 15:50:08,572 -        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 15:50:19,148 -        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 15:50:29,721 -        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 15:50:40,306 -        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 15:50:50,878 -        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 15:51:01,458 -        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 15:51:12,052 -        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 15:51:22,625 -        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 15:51:33,218 -        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 15:51:43,809 -        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 15:51:54,370 -        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 15:52:04,939 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6100, best=0.52, avg=0.50, std=0.00, steps=9.996e+07
2023-07-07 15:52:15,504 -        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 15:52:26,062 -        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 15:52:36,634 -        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 15:52:47,216 -        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 15:52:57,802 -        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 15:53:08,389 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6700, best=0.58, avg=0.57, std=0.00, steps=1.098e+08
2023-07-07 15:53:18,961 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6800, best=0.62, avg=0.61, std=0.00, steps=1.114e+08
2023-07-07 15:53:29,552 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 6900, best=0.64, avg=0.64, std=0.00, steps=1.131e+08
2023-07-07 15:53:40,126 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7000, best=0.65, avg=0.65, std=0.00, steps=1.147e+08
2023-07-07 15:53:50,714 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7100, best=0.66, avg=0.65, std=0.00, steps=1.163e+08
2023-07-07 15:54:01,281 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7200, best=0.67, avg=0.66, std=0.00, steps=1.180e+08
2023-07-07 15:54:11,858 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7300, best=0.67, avg=0.66, std=0.00, steps=1.196e+08
2023-07-07 15:54:22,434 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7400, best=0.68, avg=0.67, std=0.00, steps=1.213e+08
2023-07-07 15:54:33,021 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7500, best=0.68, avg=0.67, std=0.00, steps=1.229e+08
2023-07-07 15:54:43,607 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7600, best=0.68, avg=0.68, std=0.00, steps=1.245e+08
2023-07-07 15:54:54,190 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7700, best=0.69, avg=0.68, std=0.00, steps=1.262e+08
2023-07-07 15:55:04,756 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7800, best=0.69, avg=0.68, std=0.00, steps=1.278e+08
2023-07-07 15:55:15,312 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 7900, best=0.69, avg=0.68, std=0.00, steps=1.294e+08
2023-07-07 15:55:25,883 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8000, best=0.70, avg=0.69, std=0.00, steps=1.311e+08
2023-07-07 15:55:36,462 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8100, best=0.70, avg=0.69, std=0.00, steps=1.327e+08
2023-07-07 15:55:47,026 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8200, best=0.70, avg=0.69, std=0.00, steps=1.344e+08
2023-07-07 15:55:57,583 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8300, best=0.70, avg=0.69, std=0.00, steps=1.360e+08
2023-07-07 15:56:08,144 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8400, best=0.70, avg=0.70, std=0.00, steps=1.376e+08
2023-07-07 15:56:18,724 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8500, best=0.71, avg=0.70, std=0.00, steps=1.393e+08
2023-07-07 15:56:29,280 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8600, best=0.71, avg=0.70, std=0.00, steps=1.409e+08
2023-07-07 15:56:39,868 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8700, best=0.71, avg=0.70, std=0.00, steps=1.426e+08
2023-07-07 15:56:50,437 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8800, best=0.71, avg=0.71, std=0.00, steps=1.442e+08
2023-07-07 15:57:01,028 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 8900, best=0.71, avg=0.71, std=0.00, steps=1.458e+08
2023-07-07 15:57:11,608 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9000, best=0.72, avg=0.71, std=0.00, steps=1.475e+08
2023-07-07 15:57:22,190 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9100, best=0.72, avg=0.71, std=0.00, steps=1.491e+08
2023-07-07 15:57:32,763 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9200, best=0.72, avg=0.71, std=0.00, steps=1.507e+08
2023-07-07 15:57:43,350 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9300, best=0.72, avg=0.72, std=0.00, steps=1.524e+08
2023-07-07 15:57:53,917 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9400, best=0.73, avg=0.72, std=0.00, steps=1.540e+08
2023-07-07 15:58:04,500 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9500, best=0.73, avg=0.72, std=0.00, steps=1.557e+08
2023-07-07 15:58:15,068 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9600, best=0.73, avg=0.72, std=0.00, steps=1.573e+08
2023-07-07 15:58:25,644 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9700, best=0.73, avg=0.72, std=0.00, steps=1.589e+08
2023-07-07 15:58:36,222 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9800, best=0.73, avg=0.72, std=0.00, steps=1.606e+08
2023-07-07 15:58:46,792 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 9900, best=0.73, avg=0.73, std=0.00, steps=1.622e+08
2023-07-07 15:58:57,352 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10000, best=0.74, avg=0.73, std=0.00, steps=1.639e+08
2023-07-07 15:59:07,917 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10100, best=0.74, avg=0.73, std=0.00, steps=1.655e+08
2023-07-07 15:59:18,481 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10200, best=0.74, avg=0.73, std=0.00, steps=1.671e+08
2023-07-07 15:59:29,035 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10300, best=0.74, avg=0.73, std=0.00, steps=1.688e+08
2023-07-07 15:59:39,605 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10400, best=0.74, avg=0.73, std=0.00, steps=1.704e+08
2023-07-07 15:59:50,161 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10500, best=0.75, avg=0.74, std=0.00, steps=1.720e+08
2023-07-07 16:00:00,709 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10600, best=0.74, avg=0.74, std=0.00, steps=1.737e+08
2023-07-07 16:00:11,272 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10700, best=0.74, avg=0.74, std=0.00, steps=1.753e+08
2023-07-07 16:00:21,835 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10800, best=0.75, avg=0.74, std=0.00, steps=1.770e+08
2023-07-07 16:00:32,425 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 10900, best=0.75, avg=0.74, std=0.00, steps=1.786e+08
2023-07-07 16:00:42,987 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11000, best=0.75, avg=0.74, std=0.00, steps=1.802e+08
2023-07-07 16:00:53,550 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11100, best=0.75, avg=0.74, std=0.00, steps=1.819e+08
2023-07-07 16:01:04,103 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11200, best=0.75, avg=0.74, std=0.00, steps=1.835e+08
2023-07-07 16:01:14,659 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11300, best=0.75, avg=0.74, std=0.00, steps=1.852e+08
2023-07-07 16:01:25,214 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11400, best=0.75, avg=0.75, std=0.00, steps=1.868e+08
2023-07-07 16:01:35,768 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11500, best=0.75, avg=0.75, std=0.00, steps=1.884e+08
2023-07-07 16:01:46,351 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11600, best=0.76, avg=0.75, std=0.00, steps=1.901e+08
2023-07-07 16:01:56,912 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11700, best=0.76, avg=0.75, std=0.00, steps=1.917e+08
2023-07-07 16:02:07,476 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11800, best=0.76, avg=0.75, std=0.00, steps=1.933e+08
2023-07-07 16:02:18,035 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11900, best=0.76, avg=0.75, std=0.00, steps=1.950e+08
2023-07-07 16:02:28,509 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 0, 0, [Train]: 11999, best=0.76, avg=0.75, std=0.00, steps=1.966e+08
2023-07-07 16:02:28,509 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 16:02:28,533 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:02:28,533 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:02:28,568 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:02:42,128 -        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 16:02:54,016 -        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 16:03:05,903 -        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 16:03:17,799 -        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 16:03:29,695 -        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 16:03:41,581 -        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 16:03:53,492 -        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 16:04:05,373 -        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 16:04:17,251 -        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 16:04:29,146 -        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 16:04:41,032 -        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 16:04:52,916 -        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 16:05:04,807 -        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 16:05:16,688 -        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 16:05:28,588 -        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 16:05:40,469 -        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 16:05:52,374 -        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 16:06:04,270 -        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 16:06:16,165 -        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 16:06:28,047 -        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 16:06:39,926 -        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 16:06:51,808 -        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 16:07:03,691 -        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 16:07:15,598 -        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 16:07:27,490 -        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 16:07:39,404 -        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 16:07:51,304 -        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 16:08:03,196 -        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 16:08:15,078 -        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 16:08:26,972 -        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 16:08:38,852 -        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 16:08:50,750 -        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 16:09:02,645 -        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 16:09:14,536 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 3400, best=0.51, avg=0.50, std=0.00, steps=6.269e+07
2023-07-07 16:09:26,426 -        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 16:09:38,312 -        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 16:09:50,195 -        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 16:10:02,074 -        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 16:10:13,954 -        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 16:10:25,862 -        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 16:10:37,756 -        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 16:10:49,653 -        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 16:11:01,532 -        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 16:11:13,406 -        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 16:11:25,286 -        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 16:11:37,182 -        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 16:11:49,089 -        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 16:12:00,989 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=8.849e+07
2023-07-07 16:12:12,929 -        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 16:12:24,823 -        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 16:12:36,710 -        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 16:12:48,608 -        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 16:13:00,499 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=9.771e+07
2023-07-07 16:13:12,397 -        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 16:13:24,300 -        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 16:13:36,196 -        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 16:13:48,080 -        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 16:13:59,973 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 5800, best=0.51, avg=0.50, std=0.00, steps=1.069e+08
2023-07-07 16:14:11,855 -        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 16:14:23,756 -        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 16:14:35,645 -        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 16:14:47,553 -        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 16:14:59,454 -        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 16:15:11,336 -        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 16:15:23,239 -        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 16:15:35,131 -        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 16:15:47,027 -        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 16:15:58,915 -        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 16:16:10,822 -        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 16:16:22,714 -        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 16:16:34,613 -        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 16:16:46,531 -        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 16:16:58,433 -        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 16:17:10,342 -        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 16:17:22,231 -        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 16:17:34,116 -        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 16:17:46,005 -        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 16:17:57,928 -        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 16:18:09,826 -        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 16:18:21,707 -        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 16:18:33,612 -        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 16:18:45,512 -        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 16:18:57,401 -        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 16:19:09,284 -        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 16:19:21,163 -        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 16:19:33,061 -        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 16:19:44,938 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8700, best=0.52, avg=0.50, std=0.00, steps=1.604e+08
2023-07-07 16:19:56,847 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 16:20:08,738 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=1.641e+08
2023-07-07 16:20:20,631 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=1.659e+08
2023-07-07 16:20:32,509 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=1.677e+08
2023-07-07 16:20:44,398 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 16:20:56,266 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=1.714e+08
2023-07-07 16:21:08,157 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=1.733e+08
2023-07-07 16:21:20,041 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9500, best=0.60, avg=0.59, std=0.00, steps=1.751e+08
2023-07-07 16:21:31,930 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9600, best=0.62, avg=0.62, std=0.00, steps=1.770e+08
2023-07-07 16:21:43,822 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9700, best=0.64, avg=0.64, std=0.00, steps=1.788e+08
2023-07-07 16:21:55,717 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9800, best=0.65, avg=0.64, std=0.00, steps=1.807e+08
2023-07-07 16:22:07,608 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 9900, best=0.65, avg=0.65, std=0.00, steps=1.825e+08
2023-07-07 16:22:19,490 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10000, best=0.66, avg=0.65, std=0.00, steps=1.843e+08
2023-07-07 16:22:31,382 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10100, best=0.66, avg=0.65, std=0.00, steps=1.862e+08
2023-07-07 16:22:43,374 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10200, best=0.66, avg=0.66, std=0.00, steps=1.880e+08
2023-07-07 16:22:55,256 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10300, best=0.67, avg=0.66, std=0.00, steps=1.899e+08
2023-07-07 16:23:07,143 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10400, best=0.67, avg=0.66, std=0.00, steps=1.917e+08
2023-07-07 16:23:19,041 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10500, best=0.67, avg=0.67, std=0.00, steps=1.936e+08
2023-07-07 16:23:30,915 -        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 16:23:42,808 -        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 16:23:54,782 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 10800, best=0.68, avg=0.67, std=0.00, steps=1.991e+08
2023-07-07 16:24:06,715 -        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 16:24:18,634 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11000, best=0.68, avg=0.68, std=0.00, steps=2.028e+08
2023-07-07 16:24:30,520 -        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 16:24:42,409 -        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 16:24:54,381 -        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 16:25:06,283 -        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 16:25:18,197 -        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 16:25:30,096 -        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 16:25:42,045 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 8, 0, [Train]: 11700, best=0.70, avg=0.69, std=0.00, steps=2.157e+08
2023-07-07 16:25:53,959 -        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 16:26:05,841 -        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 16:26:17,633 -        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 16:26:17,634 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 16:26:17,659 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:26:17,659 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:26:17,692 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:26:32,515 -        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 16:26:45,761 -        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 16:26:58,986 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 300, best=0.51, avg=0.50, std=0.00, steps=6.164e+06
2023-07-07 16:27:12,177 -        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 16:27:25,363 -        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 16:27:38,544 -        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 16:27:51,722 -        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 16:28:04,907 -        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 16:28:18,085 -        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 16:28:31,272 -        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 16:28:44,449 -        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 16:28:57,652 -        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 16:29:10,850 -        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 16:29:24,033 -        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 16:29:37,253 -        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 16:29:50,450 -        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 16:30:03,632 -        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 16:30:16,881 -        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 16:30:30,098 -        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 16:30:43,337 -        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 16:30:56,523 -        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 16:31:09,704 -        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 16:31:22,912 -        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 16:31:36,109 -        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 16:31:49,300 -        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 16:32:02,509 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 2600, best=0.51, avg=0.50, std=0.00, steps=5.327e+07
2023-07-07 16:32:15,734 -        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 16:32:28,939 -        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 16:32:42,150 -        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 16:32:55,340 -        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 16:33:08,526 -        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 16:33:21,727 -        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 16:33:34,936 -        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 16:33:48,188 -        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 16:34:01,381 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=7.170e+07
2023-07-07 16:34:14,554 -        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 16:34:27,723 -        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 16:34:40,903 -        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 16:34:54,078 -        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 16:35:07,268 -        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 16:35:20,478 -        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 16:35:33,665 -        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 16:35:46,850 -        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 16:36:00,115 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 4400, best=0.51, avg=0.50, std=0.00, steps=9.013e+07
2023-07-07 16:36:13,312 -        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 16:36:26,504 -        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 16:36:39,672 -        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 16:36:52,845 -        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 16:37:06,034 -        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 16:37:19,239 -        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 16:37:32,535 -        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 16:37:45,741 -        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 16:37:58,922 -        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 16:38:12,105 -        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 16:38:25,286 -        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 16:38:38,464 -        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 16:38:51,642 -        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 16:39:04,931 -        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 16:39:18,160 -        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 16:39:31,365 -        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 16:39:44,563 -        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 16:39:57,739 -        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 16:40:10,919 -        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 16:40:24,102 -        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 16:40:37,287 -        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 16:40:50,453 -        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 16:41:03,656 -        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 16:41:16,846 -        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 16:41:30,013 -        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 16:41:43,200 -        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 16:41:56,359 -        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 16:42:09,524 -        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 16:42:22,715 -        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 16:42:35,886 -        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 16:42:49,171 -        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 16:43:02,344 -        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 16:43:15,504 -        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 16:43:28,655 -        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 16:43:41,827 -        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 16:43:55,021 -        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 16:44:08,289 -        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 16:44:21,461 -        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 16:44:34,637 -        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 16:44:47,829 -        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 16:45:00,998 -        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 16:45:14,216 -        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 16:45:27,449 -        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 16:45:40,632 -        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 16:45:53,810 -        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 16:46:06,988 -        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 16:46:20,173 -        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 16:46:33,327 -        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 16:46:46,540 -        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 16:46:59,808 -        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 16:47:13,001 -        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 16:47:26,176 -        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 16:47:39,424 -        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 16:47:52,605 -        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 16:48:05,764 -        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 16:48:18,931 -        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 16:48:32,092 -        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 16:48:45,280 -        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 16:48:58,444 -        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 16:49:11,604 -        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 16:49:24,767 -        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 16:49:37,937 -        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 16:49:51,150 -        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 16:50:04,357 -        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 16:50:17,542 -        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 16:50:30,719 -        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 16:50:43,890 -        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 16:50:57,069 -        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 16:51:10,234 -        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 16:51:23,426 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11400, best=0.57, avg=0.56, std=0.00, steps=2.335e+08
2023-07-07 16:51:36,614 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11500, best=0.59, avg=0.59, std=0.00, steps=2.355e+08
2023-07-07 16:51:49,791 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11600, best=0.60, avg=0.59, std=0.00, steps=2.376e+08
2023-07-07 16:52:02,975 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11700, best=0.60, avg=0.60, std=0.00, steps=2.396e+08
2023-07-07 16:52:16,185 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11800, best=0.61, avg=0.61, std=0.00, steps=2.417e+08
2023-07-07 16:52:29,403 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11900, best=0.62, avg=0.62, std=0.00, steps=2.437e+08
2023-07-07 16:52:42,484 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 16, 0, [Train]: 11999, best=0.63, avg=0.62, std=0.00, steps=2.458e+08
2023-07-07 16:52:42,484 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 16:52:42,510 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 16:52:42,510 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 16:52:42,542 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 16:52:59,978 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 100, best=0.51, avg=0.50, std=0.00, steps=2.482e+06
2023-07-07 16:53:15,724 -        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 16:53:31,452 -        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 16:53:47,205 -        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 16:54:02,951 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.231e+07
2023-07-07 16:54:18,691 -        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 16:54:34,438 -        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 16:54:50,172 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 800, best=0.52, avg=0.50, std=0.00, steps=1.969e+07
2023-07-07 16:55:05,925 -        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 16:55:21,651 -        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 16:55:37,380 -        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 16:55:53,112 -        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 16:56:08,859 -        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 16:56:24,598 -        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 16:56:40,321 -        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 16:56:56,048 -        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 16:57:11,783 -        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 16:57:27,516 -        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 16:57:43,261 -        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 16:57:59,001 -        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 16:58:14,743 -        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 16:58:30,471 -        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 16:58:46,220 -        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 16:59:01,952 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2400, best=0.51, avg=0.50, std=0.00, steps=5.901e+07
2023-07-07 16:59:17,689 -        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 16:59:33,423 -        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 16:59:49,174 -        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 17:00:04,912 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=6.884e+07
2023-07-07 17:00:20,633 -        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 17:00:36,377 -        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 17:00:52,127 -        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 17:01:07,875 -        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 17:01:23,605 -        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 17:01:39,335 -        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 17:01:55,060 -        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 17:02:10,817 -        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 17:02:26,553 -        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 17:02:42,288 -        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 17:02:58,032 -        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 17:03:13,763 -        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 17:03:29,496 -        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 17:03:45,217 -        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 17:04:00,955 -        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 17:04:16,687 -        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 17:04:32,413 -        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 17:04:48,148 -        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 17:05:03,892 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 4700, best=0.51, avg=0.50, std=0.00, steps=1.155e+08
2023-07-07 17:05:19,624 -        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 17:05:35,354 -        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 17:05:51,112 -        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 17:06:06,842 -        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 17:06:22,577 -        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 17:06:38,331 -        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 17:06:54,080 -        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 17:07:09,821 -        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 17:07:25,560 -        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 17:07:41,293 -        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 17:07:57,095 -        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 17:08:12,894 -        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 17:08:28,691 -        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 17:08:44,440 -        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 17:09:00,261 -        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 17:09:16,006 -        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 17:09:31,744 -        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 17:09:47,511 -        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 17:10:03,236 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=1.622e+08
2023-07-07 17:10:19,002 -        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 17:10:34,759 -        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 17:10:50,496 -        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 17:11:06,235 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=1.721e+08
2023-07-07 17:11:21,971 -        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 17:11:37,706 -        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 17:11:53,443 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=1.794e+08
2023-07-07 17:12:09,179 -        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 17:12:24,914 -        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 17:12:40,642 -        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 17:12:56,378 -        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 17:13:12,105 -        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 17:13:27,834 -        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 17:13:43,568 -        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 17:13:59,291 -        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 17:14:15,030 -        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 17:14:30,851 -        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 17:14:46,617 -        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 17:15:02,350 -        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 17:15:18,080 -        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 17:15:33,802 -        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 17:15:49,551 -        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 17:16:05,270 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.188e+08
2023-07-07 17:16:21,009 -        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 17:16:36,789 -        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 17:16:52,551 -        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 17:17:08,302 -        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 17:17:24,049 -        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 17:17:39,808 -        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 17:17:55,558 -        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 17:18:11,282 -        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 17:18:27,025 -        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 17:18:42,775 -        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 17:18:58,567 -        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 17:19:14,340 -        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 17:19:30,114 -        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 17:19:45,949 -        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 17:20:01,673 -        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 17:20:17,426 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=2.581e+08
2023-07-07 17:20:33,232 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=2.605e+08
2023-07-07 17:20:48,983 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10700, best=0.51, avg=0.50, std=0.00, steps=2.630e+08
2023-07-07 17:21:04,739 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10800, best=0.51, avg=0.50, std=0.00, steps=2.654e+08
2023-07-07 17:21:20,468 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 10900, best=0.51, avg=0.50, std=0.00, steps=2.679e+08
2023-07-07 17:21:36,188 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11000, best=0.51, avg=0.50, std=0.00, steps=2.704e+08
2023-07-07 17:21:51,994 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11100, best=0.51, avg=0.50, std=0.00, steps=2.728e+08
2023-07-07 17:22:07,820 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11200, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 17:22:23,555 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11300, best=0.51, avg=0.50, std=0.00, steps=2.777e+08
2023-07-07 17:22:39,289 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11400, best=0.51, avg=0.50, std=0.00, steps=2.802e+08
2023-07-07 17:22:55,024 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11500, best=0.51, avg=0.50, std=0.00, steps=2.826e+08
2023-07-07 17:23:10,755 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11600, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 17:23:26,491 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11700, best=0.51, avg=0.50, std=0.00, steps=2.876e+08
2023-07-07 17:23:42,320 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11800, best=0.51, avg=0.50, std=0.00, steps=2.900e+08
2023-07-07 17:23:58,069 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11900, best=0.51, avg=0.50, std=0.00, steps=2.925e+08
2023-07-07 17:24:13,688 -        meta learning: [    INFO] - [Len Lat Rep]: 32, 32, 0, [Train]: 11999, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 17:24:13,689 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 17:24:13,713 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 17:24:13,714 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 17:24:13,747 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 17:24:36,579 -        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 17:24:57,568 -        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 17:25:18,524 -        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 17:25:39,440 -        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 17:26:00,420 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 500, best=0.51, avg=0.50, std=0.00, steps=1.642e+07
2023-07-07 17:26:21,326 -        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 17:26:42,289 -        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 17:27:03,241 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 800, best=0.51, avg=0.50, std=0.00, steps=2.625e+07
2023-07-07 17:27:24,202 -        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 17:27:45,140 -        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 17:28:06,060 -        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 17:28:27,009 -        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 17:28:47,927 -        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 17:29:08,837 -        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 17:29:29,748 -        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 17:29:50,710 -        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 17:30:11,641 -        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 17:30:32,572 -        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 17:30:53,534 -        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 17:31:14,462 -        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 17:31:35,377 -        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 17:31:56,297 -        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 17:32:17,211 -        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 17:32:38,120 -        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 17:32:59,045 -        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 17:33:19,975 -        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 17:33:40,892 -        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 17:34:01,814 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 2800, best=0.51, avg=0.50, std=0.00, steps=9.178e+07
2023-07-07 17:34:22,729 -        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 17:34:43,665 -        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 17:35:04,610 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 3100, best=0.51, avg=0.50, std=0.00, steps=1.016e+08
2023-07-07 17:35:25,544 -        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 17:35:46,475 -        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 17:36:07,440 -        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 17:36:28,356 -        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 17:36:49,281 -        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 17:37:10,235 -        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 17:37:31,152 -        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 17:37:52,062 -        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 17:38:12,967 -        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 17:38:33,885 -        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 17:38:54,838 -        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 17:39:15,754 -        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 17:39:36,676 -        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 17:39:57,616 -        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 17:40:18,562 -        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 17:40:39,517 -        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 17:41:00,429 -        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 17:41:21,379 -        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 17:41:42,273 -        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 17:42:03,152 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5100, best=0.51, avg=0.50, std=0.00, steps=1.671e+08
2023-07-07 17:42:24,059 -        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 17:42:44,989 -        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 17:43:05,906 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 5400, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 17:43:26,803 -        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 17:43:47,719 -        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 17:44:08,637 -        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 17:44:29,552 -        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 17:44:50,462 -        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 17:45:11,368 -        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 17:45:32,286 -        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 17:45:53,230 -        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 17:46:14,160 -        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 17:46:35,098 -        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 17:46:56,012 -        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 17:47:16,931 -        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 17:47:37,854 -        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 17:47:58,772 -        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 17:48:19,705 -        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 17:48:40,636 -        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 17:49:01,535 -        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 17:49:22,485 -        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 17:49:43,392 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.392e+08
2023-07-07 17:50:04,307 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=2.425e+08
2023-07-07 17:50:25,219 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=2.458e+08
2023-07-07 17:50:46,159 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=2.491e+08
2023-07-07 17:51:07,064 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7700, best=0.51, avg=0.50, std=0.00, steps=2.523e+08
2023-07-07 17:51:27,975 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7800, best=0.51, avg=0.50, std=0.00, steps=2.556e+08
2023-07-07 17:51:48,898 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 7900, best=0.51, avg=0.50, std=0.00, steps=2.589e+08
2023-07-07 17:52:09,781 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8000, best=0.51, avg=0.50, std=0.00, steps=2.622e+08
2023-07-07 17:52:30,717 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8100, best=0.51, avg=0.50, std=0.00, steps=2.655e+08
2023-07-07 17:52:51,640 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8200, best=0.51, avg=0.50, std=0.00, steps=2.687e+08
2023-07-07 17:53:12,578 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8300, best=0.51, avg=0.50, std=0.00, steps=2.720e+08
2023-07-07 17:53:33,511 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8400, best=0.51, avg=0.50, std=0.00, steps=2.753e+08
2023-07-07 17:53:54,472 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8500, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 17:54:15,386 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8600, best=0.51, avg=0.50, std=0.00, steps=2.818e+08
2023-07-07 17:54:36,297 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8700, best=0.51, avg=0.50, std=0.00, steps=2.851e+08
2023-07-07 17:54:57,214 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8800, best=0.51, avg=0.50, std=0.00, steps=2.884e+08
2023-07-07 17:55:18,123 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 8900, best=0.51, avg=0.50, std=0.00, steps=2.917e+08
2023-07-07 17:55:39,054 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9000, best=0.51, avg=0.50, std=0.00, steps=2.949e+08
2023-07-07 17:55:59,995 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=2.982e+08
2023-07-07 17:56:20,912 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.015e+08
2023-07-07 17:56:41,812 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9300, best=0.51, avg=0.50, std=0.00, steps=3.048e+08
2023-07-07 17:57:02,721 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9400, best=0.51, avg=0.50, std=0.00, steps=3.081e+08
2023-07-07 17:57:23,665 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9500, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 17:57:44,589 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9600, best=0.51, avg=0.50, std=0.00, steps=3.146e+08
2023-07-07 17:58:05,545 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9700, best=0.51, avg=0.50, std=0.00, steps=3.179e+08
2023-07-07 17:58:26,489 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9800, best=0.51, avg=0.50, std=0.00, steps=3.212e+08
2023-07-07 17:58:47,408 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=3.244e+08
2023-07-07 17:59:08,308 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10000, best=0.51, avg=0.50, std=0.00, steps=3.277e+08
2023-07-07 17:59:29,243 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10100, best=0.51, avg=0.50, std=0.00, steps=3.310e+08
2023-07-07 17:59:50,156 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10200, best=0.51, avg=0.50, std=0.00, steps=3.343e+08
2023-07-07 18:00:11,064 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10300, best=0.51, avg=0.50, std=0.00, steps=3.375e+08
2023-07-07 18:00:31,985 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10400, best=0.51, avg=0.50, std=0.00, steps=3.408e+08
2023-07-07 18:00:52,893 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10500, best=0.51, avg=0.50, std=0.00, steps=3.441e+08
2023-07-07 18:01:13,813 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=3.474e+08
2023-07-07 18:01:34,713 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10700, best=0.55, avg=0.54, std=0.00, steps=3.507e+08
2023-07-07 18:01:55,635 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10800, best=0.55, avg=0.55, std=0.00, steps=3.539e+08
2023-07-07 18:02:16,556 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 10900, best=0.56, avg=0.55, std=0.00, steps=3.572e+08
2023-07-07 18:02:37,472 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11000, best=0.57, avg=0.56, std=0.00, steps=3.605e+08
2023-07-07 18:02:58,415 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11100, best=0.58, avg=0.57, std=0.00, steps=3.638e+08
2023-07-07 18:03:19,352 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11200, best=0.58, avg=0.58, std=0.00, steps=3.670e+08
2023-07-07 18:03:40,299 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11300, best=0.58, avg=0.58, std=0.00, steps=3.703e+08
2023-07-07 18:04:01,222 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11400, best=0.59, avg=0.58, std=0.00, steps=3.736e+08
2023-07-07 18:04:22,138 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11500, best=0.59, avg=0.58, std=0.00, steps=3.769e+08
2023-07-07 18:04:43,081 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11600, best=0.59, avg=0.59, std=0.00, steps=3.801e+08
2023-07-07 18:05:03,993 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11700, best=0.59, avg=0.59, std=0.00, steps=3.834e+08
2023-07-07 18:05:24,902 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11800, best=0.59, avg=0.59, std=0.00, steps=3.867e+08
2023-07-07 18:05:45,854 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11900, best=0.60, avg=0.59, std=0.00, steps=3.900e+08
2023-07-07 18:06:06,560 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 0, 0, [Train]: 11999, best=0.60, avg=0.59, std=0.00, steps=3.932e+08
2023-07-07 18:06:06,560 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 18:06:06,586 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:06:06,586 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:06:06,619 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:06:30,646 -        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 18:06:52,864 -        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 18:07:15,064 -        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 18:07:37,250 -        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 18:07:59,441 -        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 18:08:21,629 -        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 18:08:43,827 -        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 18:09:06,009 -        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 18:09:28,199 -        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 18:09:50,377 -        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 18:10:12,587 -        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 18:10:34,788 -        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 18:10:57,003 -        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 18:11:19,194 -        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 18:11:41,366 -        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 18:12:03,554 -        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 18:12:25,742 -        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 18:12:47,911 -        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 18:13:10,101 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 1900, best=0.51, avg=0.50, std=0.00, steps=6.619e+07
2023-07-07 18:13:32,290 -        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 18:13:54,464 -        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 18:14:16,664 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 2200, best=0.50, avg=0.50, std=0.00, steps=7.663e+07
2023-07-07 18:14:38,883 -        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 18:15:01,050 -        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 18:15:23,224 -        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 18:15:45,402 -        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 18:16:07,580 -        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 18:16:29,750 -        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 18:16:51,938 -        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 18:17:14,165 -        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 18:17:36,375 -        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 18:17:58,576 -        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 18:18:20,769 -        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 18:18:43,022 -        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 18:19:05,205 -        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 18:19:27,378 -        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 18:19:49,559 -        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 18:20:11,755 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 3800, best=0.51, avg=0.50, std=0.00, steps=1.323e+08
2023-07-07 18:20:33,957 -        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 18:20:56,159 -        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 18:21:18,367 -        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 18:21:40,555 -        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 18:22:02,752 -        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 18:22:24,961 -        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 18:22:47,178 -        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 18:23:09,345 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.602e+08
2023-07-07 18:23:31,522 -        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 18:23:53,720 -        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 18:24:15,909 -        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 18:24:38,067 -        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 18:25:00,241 -        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 18:25:22,439 -        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 18:25:44,641 -        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 18:26:06,829 -        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 18:26:29,005 -        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 18:26:51,171 -        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 18:27:13,368 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 5700, best=0.51, avg=0.50, std=0.00, steps=1.985e+08
2023-07-07 18:27:35,568 -        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 18:27:57,750 -        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 18:28:19,936 -        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 18:28:42,162 -        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 18:29:04,334 -        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 18:29:26,513 -        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 18:29:48,674 -        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 18:30:10,861 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6500, best=0.51, avg=0.50, std=0.00, steps=2.263e+08
2023-07-07 18:30:33,050 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6600, best=0.57, avg=0.57, std=0.00, steps=2.298e+08
2023-07-07 18:30:55,227 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6700, best=0.58, avg=0.57, std=0.00, steps=2.333e+08
2023-07-07 18:31:17,398 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6800, best=0.58, avg=0.57, std=0.00, steps=2.368e+08
2023-07-07 18:31:39,589 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 6900, best=0.58, avg=0.57, std=0.00, steps=2.403e+08
2023-07-07 18:32:01,789 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7000, best=0.58, avg=0.57, std=0.00, steps=2.437e+08
2023-07-07 18:32:23,993 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7100, best=0.58, avg=0.57, std=0.00, steps=2.472e+08
2023-07-07 18:32:46,185 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7200, best=0.58, avg=0.57, std=0.00, steps=2.507e+08
2023-07-07 18:33:08,372 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7300, best=0.58, avg=0.57, std=0.00, steps=2.542e+08
2023-07-07 18:33:30,557 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7400, best=0.58, avg=0.57, std=0.00, steps=2.577e+08
2023-07-07 18:33:52,752 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7500, best=0.58, avg=0.57, std=0.00, steps=2.612e+08
2023-07-07 18:34:14,936 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7600, best=0.58, avg=0.57, std=0.00, steps=2.646e+08
2023-07-07 18:34:37,094 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7700, best=0.58, avg=0.58, std=0.00, steps=2.681e+08
2023-07-07 18:34:59,280 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7800, best=0.59, avg=0.58, std=0.00, steps=2.716e+08
2023-07-07 18:35:21,445 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 7900, best=0.59, avg=0.59, std=0.00, steps=2.751e+08
2023-07-07 18:35:43,618 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8000, best=0.60, avg=0.59, std=0.00, steps=2.786e+08
2023-07-07 18:36:05,797 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8100, best=0.60, avg=0.59, std=0.00, steps=2.820e+08
2023-07-07 18:36:28,001 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8200, best=0.60, avg=0.60, std=0.00, steps=2.855e+08
2023-07-07 18:36:50,180 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8300, best=0.61, avg=0.60, std=0.00, steps=2.890e+08
2023-07-07 18:37:12,375 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8400, best=0.60, avg=0.60, std=0.00, steps=2.925e+08
2023-07-07 18:37:34,591 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8500, best=0.61, avg=0.60, std=0.00, steps=2.960e+08
2023-07-07 18:37:56,778 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8600, best=0.61, avg=0.61, std=0.00, steps=2.995e+08
2023-07-07 18:38:18,971 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8700, best=0.61, avg=0.61, std=0.00, steps=3.029e+08
2023-07-07 18:38:41,134 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8800, best=0.61, avg=0.61, std=0.00, steps=3.064e+08
2023-07-07 18:39:03,345 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 8900, best=0.62, avg=0.61, std=0.00, steps=3.099e+08
2023-07-07 18:39:25,522 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9000, best=0.62, avg=0.61, std=0.00, steps=3.134e+08
2023-07-07 18:39:47,711 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9100, best=0.62, avg=0.61, std=0.00, steps=3.169e+08
2023-07-07 18:40:09,900 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9200, best=0.62, avg=0.61, std=0.00, steps=3.203e+08
2023-07-07 18:40:32,082 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9300, best=0.62, avg=0.62, std=0.00, steps=3.238e+08
2023-07-07 18:40:54,272 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9400, best=0.62, avg=0.62, std=0.00, steps=3.273e+08
2023-07-07 18:41:16,482 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9500, best=0.62, avg=0.62, std=0.00, steps=3.308e+08
2023-07-07 18:41:38,688 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9600, best=0.62, avg=0.62, std=0.00, steps=3.343e+08
2023-07-07 18:42:00,908 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9700, best=0.63, avg=0.62, std=0.00, steps=3.378e+08
2023-07-07 18:42:23,098 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9800, best=0.63, avg=0.62, std=0.00, steps=3.412e+08
2023-07-07 18:42:45,303 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 9900, best=0.63, avg=0.62, std=0.00, steps=3.447e+08
2023-07-07 18:43:07,489 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10000, best=0.63, avg=0.62, std=0.00, steps=3.482e+08
2023-07-07 18:43:29,693 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10100, best=0.63, avg=0.62, std=0.00, steps=3.517e+08
2023-07-07 18:43:51,875 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10200, best=0.63, avg=0.62, std=0.00, steps=3.552e+08
2023-07-07 18:44:14,066 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10300, best=0.63, avg=0.63, std=0.00, steps=3.586e+08
2023-07-07 18:44:36,286 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10400, best=0.63, avg=0.63, std=0.00, steps=3.621e+08
2023-07-07 18:44:58,462 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10500, best=0.63, avg=0.63, std=0.00, steps=3.656e+08
2023-07-07 18:45:20,672 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10600, best=0.63, avg=0.63, std=0.00, steps=3.691e+08
2023-07-07 18:45:42,912 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10700, best=0.63, avg=0.63, std=0.00, steps=3.726e+08
2023-07-07 18:46:05,133 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10800, best=0.63, avg=0.63, std=0.00, steps=3.760e+08
2023-07-07 18:46:27,399 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 10900, best=0.64, avg=0.63, std=0.00, steps=3.795e+08
2023-07-07 18:46:49,637 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11000, best=0.63, avg=0.63, std=0.00, steps=3.830e+08
2023-07-07 18:47:11,808 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11100, best=0.64, avg=0.63, std=0.00, steps=3.865e+08
2023-07-07 18:47:33,994 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11200, best=0.64, avg=0.63, std=0.00, steps=3.900e+08
2023-07-07 18:47:56,159 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11300, best=0.64, avg=0.63, std=0.00, steps=3.935e+08
2023-07-07 18:48:18,328 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11400, best=0.64, avg=0.63, std=0.00, steps=3.969e+08
2023-07-07 18:48:40,514 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11500, best=0.64, avg=0.63, std=0.00, steps=4.004e+08
2023-07-07 18:49:02,678 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11600, best=0.64, avg=0.63, std=0.00, steps=4.039e+08
2023-07-07 18:49:24,855 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11700, best=0.64, avg=0.63, std=0.00, steps=4.074e+08
2023-07-07 18:49:47,076 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11800, best=0.64, avg=0.63, std=0.00, steps=4.109e+08
2023-07-07 18:50:09,266 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11900, best=0.64, avg=0.63, std=0.00, steps=4.143e+08
2023-07-07 18:50:31,267 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 8, 0, [Train]: 11999, best=0.64, avg=0.64, std=0.00, steps=4.178e+08
2023-07-07 18:50:31,269 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 18:50:31,293 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 18:50:31,293 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 18:50:31,325 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 18:50:56,658 -        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 18:51:20,130 -        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 18:51:43,610 -        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 18:52:07,097 -        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 18:52:30,576 -        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 18:52:54,043 -        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 18:53:17,536 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 700, best=0.51, avg=0.50, std=0.00, steps=2.584e+07
2023-07-07 18:53:41,005 -        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 18:54:04,490 -        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 18:54:27,987 -        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 18:54:51,465 -        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 18:55:14,942 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 1200, best=0.51, avg=0.50, std=0.00, steps=4.427e+07
2023-07-07 18:55:38,431 -        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 18:56:01,920 -        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 18:56:25,412 -        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 18:56:48,891 -        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 18:57:12,368 -        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 18:57:35,871 -        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 18:57:59,372 -        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 18:58:22,882 -        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 18:58:46,365 -        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 18:59:09,878 -        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 18:59:33,369 -        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 18:59:56,866 -        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 19:00:20,330 -        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 19:00:43,794 -        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 19:01:07,282 -        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 19:01:30,736 -        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 19:01:54,251 -        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 19:02:17,774 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3000, best=0.51, avg=0.50, std=0.00, steps=1.106e+08
2023-07-07 19:02:41,302 -        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 19:03:04,798 -        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 19:03:28,271 -        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 19:03:51,724 -        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 19:04:15,234 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 3500, best=0.51, avg=0.50, std=0.00, steps=1.291e+08
2023-07-07 19:04:38,715 -        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 19:05:02,217 -        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 19:05:25,682 -        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 19:05:49,172 -        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 19:06:12,637 -        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 19:06:36,109 -        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 19:06:59,633 -        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 19:07:23,122 -        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 19:07:46,608 -        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 19:08:10,083 -        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 19:08:33,550 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.696e+08
2023-07-07 19:08:57,029 -        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 19:09:20,492 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 4800, best=0.51, avg=0.50, std=0.00, steps=1.770e+08
2023-07-07 19:09:43,975 -        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 19:10:07,482 -        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 19:10:30,981 -        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 19:10:54,461 -        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 19:11:17,935 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5300, best=0.51, avg=0.50, std=0.00, steps=1.954e+08
2023-07-07 19:11:41,411 -        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 19:12:04,919 -        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 19:12:28,432 -        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 19:12:51,924 -        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 19:13:15,417 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 5800, best=0.50, avg=0.50, std=0.00, steps=2.138e+08
2023-07-07 19:13:38,884 -        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 19:14:02,363 -        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 19:14:25,841 -        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 19:14:49,361 -        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 19:15:12,869 -        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 19:15:36,338 -        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 19:15:59,812 -        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 19:16:23,285 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 6600, best=0.51, avg=0.50, std=0.00, steps=2.433e+08
2023-07-07 19:16:46,776 -        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 19:17:10,258 -        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 19:17:33,757 -        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 19:17:57,224 -        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 19:18:20,708 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.618e+08
2023-07-07 19:18:44,179 -        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 19:19:07,646 -        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 19:19:31,118 -        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 19:19:54,604 -        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 19:20:18,075 -        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 19:20:41,556 -        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 19:21:05,011 -        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 19:21:28,490 -        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 19:21:51,969 -        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 19:22:15,448 -        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 19:22:38,940 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8200, best=0.53, avg=0.52, std=0.00, steps=3.023e+08
2023-07-07 19:23:02,421 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8300, best=0.55, avg=0.54, std=0.00, steps=3.060e+08
2023-07-07 19:23:25,890 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8400, best=0.55, avg=0.55, std=0.00, steps=3.097e+08
2023-07-07 19:23:49,381 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8500, best=0.55, avg=0.55, std=0.00, steps=3.134e+08
2023-07-07 19:24:12,863 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8600, best=0.55, avg=0.55, std=0.00, steps=3.171e+08
2023-07-07 19:24:36,342 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8700, best=0.55, avg=0.55, std=0.00, steps=3.208e+08
2023-07-07 19:24:59,841 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8800, best=0.55, avg=0.55, std=0.00, steps=3.244e+08
2023-07-07 19:25:23,315 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 8900, best=0.55, avg=0.55, std=0.00, steps=3.281e+08
2023-07-07 19:25:46,786 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9000, best=0.55, avg=0.55, std=0.00, steps=3.318e+08
2023-07-07 19:26:10,266 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9100, best=0.55, avg=0.55, std=0.00, steps=3.355e+08
2023-07-07 19:26:33,744 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9200, best=0.55, avg=0.55, std=0.00, steps=3.392e+08
2023-07-07 19:26:57,206 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9300, best=0.55, avg=0.55, std=0.00, steps=3.429e+08
2023-07-07 19:27:20,681 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9400, best=0.55, avg=0.55, std=0.00, steps=3.466e+08
2023-07-07 19:27:44,158 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9500, best=0.55, avg=0.55, std=0.00, steps=3.502e+08
2023-07-07 19:28:07,627 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9600, best=0.55, avg=0.55, std=0.00, steps=3.539e+08
2023-07-07 19:28:31,121 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9700, best=0.56, avg=0.55, std=0.00, steps=3.576e+08
2023-07-07 19:28:54,604 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9800, best=0.56, avg=0.56, std=0.00, steps=3.613e+08
2023-07-07 19:29:18,077 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 9900, best=0.57, avg=0.56, std=0.00, steps=3.650e+08
2023-07-07 19:29:41,570 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10000, best=0.57, avg=0.56, std=0.00, steps=3.687e+08
2023-07-07 19:30:05,029 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10100, best=0.57, avg=0.57, std=0.00, steps=3.724e+08
2023-07-07 19:30:28,521 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10200, best=0.57, avg=0.57, std=0.00, steps=3.760e+08
2023-07-07 19:30:51,995 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10300, best=0.57, avg=0.57, std=0.00, steps=3.797e+08
2023-07-07 19:31:15,468 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10400, best=0.58, avg=0.57, std=0.00, steps=3.834e+08
2023-07-07 19:31:38,941 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10500, best=0.58, avg=0.57, std=0.00, steps=3.871e+08
2023-07-07 19:32:02,443 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10600, best=0.59, avg=0.58, std=0.00, steps=3.908e+08
2023-07-07 19:32:25,918 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10700, best=0.59, avg=0.58, std=0.00, steps=3.945e+08
2023-07-07 19:32:49,396 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10800, best=0.59, avg=0.59, std=0.00, steps=3.982e+08
2023-07-07 19:33:12,934 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 10900, best=0.59, avg=0.59, std=0.00, steps=4.019e+08
2023-07-07 19:33:36,425 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11000, best=0.60, avg=0.59, std=0.00, steps=4.055e+08
2023-07-07 19:33:59,886 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11100, best=0.60, avg=0.59, std=0.00, steps=4.092e+08
2023-07-07 19:34:23,357 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11200, best=0.60, avg=0.60, std=0.00, steps=4.129e+08
2023-07-07 19:34:46,834 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11300, best=0.60, avg=0.60, std=0.00, steps=4.166e+08
2023-07-07 19:35:10,343 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11400, best=0.60, avg=0.60, std=0.00, steps=4.203e+08
2023-07-07 19:35:33,844 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11500, best=0.60, avg=0.60, std=0.00, steps=4.240e+08
2023-07-07 19:35:57,337 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11600, best=0.61, avg=0.60, std=0.00, steps=4.277e+08
2023-07-07 19:36:20,828 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11700, best=0.61, avg=0.60, std=0.00, steps=4.313e+08
2023-07-07 19:36:44,316 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11800, best=0.61, avg=0.60, std=0.00, steps=4.350e+08
2023-07-07 19:37:07,790 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11900, best=0.61, avg=0.60, std=0.00, steps=4.387e+08
2023-07-07 19:37:31,039 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 16, 0, [Train]: 11999, best=0.61, avg=0.60, std=0.00, steps=4.424e+08
2023-07-07 19:37:31,040 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
2023-07-07 19:37:31,065 -            MLPPolicy: [    INFO] - MLPPolicy.num_params = 50945
2023-07-07 19:37:31,065 -        meta learning: [    INFO] - [Total Params]: params=50945
2023-07-07 19:37:31,096 -           SimManager: [    INFO] - use_for_loop=False
2023-07-07 19:37:58,983 -        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 19:38:25,031 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 200, best=0.51, avg=0.50, std=0.00, steps=8.233e+06
2023-07-07 19:38:51,058 -        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 19:39:17,105 -        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 19:39:43,129 -        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 19:40:09,213 -        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 19:40:35,251 -        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 19:41:01,307 -        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 19:41:27,403 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 900, best=0.51, avg=0.50, std=0.00, steps=3.690e+07
2023-07-07 19:41:53,420 -        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 19:42:19,433 -        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 19:42:45,476 -        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 19:43:11,567 -        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 19:43:37,640 -        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 19:44:03,680 -        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 19:44:29,739 -        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 19:44:55,862 -        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 19:45:21,908 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 1800, best=0.51, avg=0.50, std=0.00, steps=7.377e+07
2023-07-07 19:45:47,941 -        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 19:46:14,016 -        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 19:46:40,053 -        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 19:47:06,071 -        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 19:47:32,111 -        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 19:47:58,191 -        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 19:48:24,252 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 2500, best=0.51, avg=0.50, std=0.00, steps=1.024e+08
2023-07-07 19:48:50,317 -        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 19:49:16,390 -        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 19:49:42,432 -        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 19:50:08,455 -        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 19:50:34,531 -        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 19:51:00,604 -        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 19:51:26,635 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3200, best=0.51, avg=0.50, std=0.00, steps=1.311e+08
2023-07-07 19:51:52,683 -        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 19:52:18,723 -        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 19:52:44,738 -        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 19:53:10,755 -        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 19:53:36,761 -        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 19:54:02,804 -        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 19:54:28,880 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 3900, best=0.51, avg=0.50, std=0.00, steps=1.598e+08
2023-07-07 19:54:54,891 -        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 19:55:20,909 -        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 19:55:46,971 -        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 19:56:13,034 -        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 19:56:39,058 -        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 19:57:05,113 -        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 19:57:31,160 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 4600, best=0.51, avg=0.50, std=0.00, steps=1.885e+08
2023-07-07 19:57:57,179 -        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 19:58:23,201 -        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 19:58:49,223 -        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 19:59:15,238 -        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 19:59:41,258 -        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 20:00:07,275 -        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 20:00:33,309 -        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 20:00:59,366 -        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 20:01:25,370 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 5500, best=0.51, avg=0.50, std=0.00, steps=2.253e+08
2023-07-07 20:01:51,413 -        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 20:02:17,461 -        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 20:02:43,542 -        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 20:03:09,608 -        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 20:03:35,630 -        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 20:04:01,658 -        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 20:04:27,712 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6200, best=0.51, avg=0.50, std=0.00, steps=2.540e+08
2023-07-07 20:04:53,769 -        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 20:05:19,802 -        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 20:05:45,858 -        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 20:06:11,894 -        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 20:06:37,923 -        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 20:07:03,990 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6800, best=0.51, avg=0.50, std=0.00, steps=2.786e+08
2023-07-07 20:07:30,011 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 6900, best=0.51, avg=0.50, std=0.00, steps=2.827e+08
2023-07-07 20:07:56,085 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7000, best=0.51, avg=0.50, std=0.00, steps=2.868e+08
2023-07-07 20:08:22,158 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7100, best=0.51, avg=0.50, std=0.00, steps=2.909e+08
2023-07-07 20:08:48,202 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7200, best=0.51, avg=0.50, std=0.00, steps=2.950e+08
2023-07-07 20:09:14,213 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7300, best=0.51, avg=0.50, std=0.00, steps=2.990e+08
2023-07-07 20:09:40,262 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7400, best=0.51, avg=0.50, std=0.00, steps=3.031e+08
2023-07-07 20:10:06,282 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7500, best=0.51, avg=0.50, std=0.00, steps=3.072e+08
2023-07-07 20:10:32,317 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 7600, best=0.51, avg=0.50, std=0.00, steps=3.113e+08
2023-07-07 20:10:58,358 -        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 20:11:24,381 -        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 20:11:50,413 -        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 20:12:16,444 -        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 20:12:42,487 -        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 20:13:08,542 -        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 20:13:34,582 -        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 20:14:00,625 -        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 20:14:26,659 -        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 20:14:52,704 -        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 20:15:18,792 -        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 20:15:44,827 -        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 20:16:10,846 -        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 20:16:36,906 -        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 20:17:02,936 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9100, best=0.51, avg=0.50, std=0.00, steps=3.728e+08
2023-07-07 20:17:28,996 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9200, best=0.51, avg=0.50, std=0.00, steps=3.769e+08
2023-07-07 20:17:55,018 -        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 20:18:21,063 -        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 20:18:47,139 -        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 20:19:13,158 -        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 20:19:39,156 -        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 20:20:05,198 -        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 20:20:31,243 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 9900, best=0.51, avg=0.50, std=0.00, steps=4.055e+08
2023-07-07 20:20:57,243 -        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 20:21:23,262 -        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 20:21:49,284 -        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 20:22:15,303 -        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 20:22:41,356 -        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 20:23:07,417 -        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 20:23:33,445 -        meta learning: [    INFO] - [Len Lat Rep]: 64, 32, 0, [Train]: 10600, best=0.51, avg=0.50, std=0.00, steps=4.342e+08
2023-07-07 20:23:59,483 -        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 20:24:25,546 -        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 20:24:51,584 -        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 20:25:17,632 -        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 20:25:43,673 -        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 20:26:09,691 -        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 20:26:35,741 -        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 20:27:01,810 -        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 20:27:27,874 -        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 20:27:53,901 -        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 20:28:19,926 -        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 20:28:45,961 -        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 20:29:12,006 -        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 20:29:37,828 -        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 20:29:37,829 -        meta learning: [    INFO] - [OUTPUT DIR]: /data/anonymous/meta/train/PGPE-GruPolicy-SeqTask--20230707-135829
