Cadene 06573d7f67 online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered

2024-04-10 11:34:01 +00:00

..

datasets

online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered

2024-04-10 11:34:01 +00:00

envs

rename handle -> task

2024-04-08 14:54:52 +00:00

policies

online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered

2024-04-10 11:34:01 +00:00

logger.py

fix wandb artifact name and add disable option

2024-03-15 13:56:55 +00:00

transforms.py

fix train.py, stats, eval.py (training is running)

2024-04-05 09:31:39 +00:00

utils.py

fix memory leak due to itertools.cycle

2024-04-05 10:59:32 +00:00