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

Offline Reinforcement Learning on D4RL mujoco-hopper (med)

95.4Normalized ScoreMOREL

Evaluation Results

Method	Links
MOREL2021.10		95.4
COMBO2021.10		94.9
ROMI-CQL2021.10		72.3
CQL2021.10		66.6
BAIL2021.10		57.5
BCQ2021.10		53.4
BEAR2021.10		50.8
ROMI-BCQ2021.10		50
MOPO2021.10		48
BC2021.10		40
Repb-SDE2021.10		11.2
BRAC-P2021.10		1
BRAC-v2021.10		0.7