ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo walker2d-random v2Follow37.3Normalized Average ReturnMOReL-1.4928.57918.6528.721Apr 16, 2025Evaluation ResultsMethodMethodLinksNormalized Average ReturnMOReL2025.0437.3VIPO-MOBILE2025.0420MOBILE2025.0417.9DQL2025.0414.1VIPO-MOPO2025.049.5IQL2025.047.7MOPO*Retrained on v2=trueRetrained on v2=true2025.047.4COMBO2025.047CQL2025.045.4TD3+BC2025.041.4RAMBO2025.040