Alexander Soare c50a13ab31 draft

2024-04-17 10:50:54 +01:00

..

act.yaml

draft

2024-04-17 10:50:54 +01:00

diffusion.yaml

backup wip

2024-04-16 12:51:32 +01:00

tdmpc.yaml

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