29 次代码提交 (9060da06-e64b-47ce-b792-5619dd26774c)

作者 SHA1 备注 提交日期
Andrew Cohen 9060da06 Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer 3 年前
Andrew Cohen 4b58527c checkout ppo/optimizer from main 3 年前
Andrew Cohen e37c5a98 Merge branch 'master' into develop-coma2-trainer 3 年前
GitHub 67e945f0 clean ups (#5003) 3 年前
Ervin Teng 4da2e22e Fix Team Cumulative Reward 3 年前
Ervin Teng 4b159789 Add PushBlockCollab config and fix some stuff 3 年前
Ervin Teng c6904f86 Group reward function 3 年前
Ervin Teng b3958a8d Buffer fixes 3 年前
Ervin Teng a4fcbb63 Right loss function for stability, fix some pypi 3 年前
Ervin Teng 9bc88c41 Running COMA (not sure if learning) 3 年前
Ervin Teng 08db7c2f Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer-mm 3 年前
Andrew Cohen 98d647de MultiInputNetBody 3 年前
Andrew Cohen 418cc778 coma trainer and optimizer 3 年前
Andrew Cohen 3f7d68b8 fix test policy 3 年前
Andrew Cohen 00b891df fix sac shared 3 年前
Andrew Cohen d81d0be3 fix agent processor test 3 年前
Andrew Cohen 66742dc8 test for SharedActorCritic 3 年前
Andrew Cohen c74dca9f add SharedActorCritic 3 年前
Ervin Teng 24ee4bd5 Merge remote-tracking branch 'origin/develop-critic-optimizer' into develop-critic-optimizer 3 年前
Andrew Cohen 6828713c fix saver test 3 年前
Andrew Cohen 9b92f5fb remove commented code 3 年前
Ervin Teng c675393c Move value network for SAC to device 3 年前
Andrew Cohen 8efdeeb0 make critic a property 3 年前
Ervin Teng 1831044a Update SAC to use separate policy 3 年前
Andrew Cohen 543f22bc fix test_networks 3 年前
Andrew Cohen 3aec18a1 fix precommit errors 3 年前
Andrew Cohen 6bd396ee add critic to optimizer, ppo runs 3 年前
Andrew Cohen f73b9dba update policy to not use critic 3 年前
Andrew Cohen eeabb974 Separate Actor/Critic, remove ActorCritics 3 年前