Offline Reinforcement Learning on D4RL mujoco-halfcheetah (med) benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on D4RL mujoco-halfcheetah (med)

69.5Normalized ScoreMOPO

Evaluation Results

Method	Links
MOPO2021.10		69.5
Repb-SDE2021.10		67.4
COMBO2021.10		54.2
ROMI-CQL2021.10		49.1
CQL2021.10		49
BCQ2021.10		47.1
ROMI-BCQ2021.10		46.2
BAIL2021.10		43.3
BEAR2021.10		43.1
MOREL2021.10		42.1
BC2021.10		39.2
BRAC-v2021.10		1.7
BRAC-P2021.10		0.9