ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo walker2d-medium v2Offline Reinforcement Learning on D4RL Gym MuJoCo walker2d-medium v2Follow93.1Normalized ReturnVIPO-MOBILE77.18881.31985.4589.581Apr 16, 2025Evaluation resultsMethodMethodLinksNormalized ReturnVIPO-MOBILE2025.0493.1VIPO-MOPO2025.0487.9MOBILE2025.0487.7DQL2025.0487RAMBO2025.0484.9MOPO*Retrained on v2=trueRetrained on v2=true2025.0484.1COMBO2025.0481.9TD3+BC2025.0479.7CQL2025.0479.5IQL2025.0478.3MOReL2025.0477.8