Offline Reinforcement Learning on D4RL maze2d-large dense benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on D4RL maze2d-large dense

133.8Normalized ScoreBEAR

Evaluation Results

Method	Links
BEAR2021.10		133.8
ROMI-BCQ2021.10		124
COMBO2021.10		100.2
BCQ2021.10		75.2
BAIL2021.10		58.2
CQL2021.10		46.9
ROMI-CQL2021.10		44
MOPO2021.10		36.8
Repb-SDE2021.10		7.9
BC2021.10		-0.3
MOREL2021.10		-3.2
BRAC-P2021.10		-4.7
BRAC-v2021.10		-7