Offline Reinforcement Learning on antmaze large-play benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on antmaze large-play

78.2ScoreGCPC

Evaluation Results

Method	Links
GCPC2023.07		78.2
TAP2023.07		74
IQL2023.07		50
GCIQL2023.07		40
IQL2022.06		39.6
IQL+smoothing2022.06		38.3
CQL2023.07		36.4
RvS-G2023.07		35.6
ROMI+BCQ2022.06		20.2
RORL2022.06		16.3
CQL2022.06		15.8
DWSL2023.07		15.2
WGCSL2023.07		0.6
TD3+BC2022.06		0.2
BC2022.06		0
AWAC2022.06		0
BC2023.07		0
DT2023.07		0