ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo hopper-medium-expert v2Follow113.2Normalized Average ReturnVIPO-MOBILE80.33688.86897.4105.932Apr 16, 2025Evaluation ResultsMethodMethodLinksNormalized Average ReturnVIPO-MOBILE2025.04113.2MOBILE2025.04112.6TD3+BC2025.04112.2DQL2025.04111.1COMBO2025.04111.1MOReL2025.04108.7VIPO-MOPO2025.04104.5CQL2025.0496.9IQL2025.0491.5RAMBO2025.0488.2MOPO*Retrained on v2=trueRetrained on v2=true2025.0481.6