ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo hopper-medium v2Offline Reinforcement Learning on D4RL Gym MuJoCo hopper-medium v2Follow107.7Normalized Average ReturnVIPO-MOBILE60.06872.43484.897.166Apr 16, 2025Evaluation resultsMethodMethodLinksNormalized Average ReturnVIPO-MOBILE2025.04107.7MOBILE2025.04106.6TD3+BC2025.0499.5COMBO2025.0497.2MOReL2025.0495.4DQL2025.0490.5RAMBO2025.0487VIPO-MOPO2025.0473.5IQL2025.0466.3MOPO*Retrained on v2=trueRetrained on v2=true2025.0462.8CQL2025.0461.9