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

..

aloha.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

factory.py

Add gym-aloha, rename simxarm -> xarm, refactor

2024-04-08 16:24:11 +02:00

pusht.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

utils.py

test_datasets.py are passing!

2024-04-08 14:16:57 +00:00

xarm.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