Alexander Soare 6d0a45a97d ready for review

2024-04-12 11:36:52 +01:00

..

act

ready for review

2024-04-12 11:36:52 +01:00

diffusion

ready for review

2024-04-12 11:36:52 +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

ready for review

2024-04-12 11:36:52 +01:00