Alexander Soare 94cc22da9e Merge remote-tracking branch 'upstream/main' into refactor_dp

2024-04-11 17:52:10 +01:00

..

act

backup wip

2024-04-11 17:51:35 +01:00

diffusion

backup wip

2024-04-11 17:51:35 +01:00

tdmpc

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

Merge remote-tracking branch 'upstream/main' into refactor_dp

2024-04-11 17:52:10 +01:00

utils.py

backup wip

2024-04-11 17:51:35 +01:00