Alexander Soare 55e484124a draft pr

2024-04-12 17:03:59 +01:00

..

env

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

policy

draft pr

2024-04-12 17:03:59 +01:00

default.yaml

fix environment seeding

2024-03-26 10:10:43 +00:00