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

..

eval.py

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

train.py

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

visualize_dataset.py

WIP

2024-04-04 15:31:03 +00:00