ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo halfcheetah-medium-replay v2Offline Reinforcement Learning on D4RL Gym MuJoCo halfcheetah-medium-replay v2Follow77.2Normalized Average ReturnVIPO-MOBILE38.7248.7158.768.69Apr 16, 2025Evaluation resultsMethodMethodLinksNormalized Average ReturnVIPO-MOBILE2025.0477.2VIPO-MOPO2025.0473MOPO*Retrained on v2=trueRetrained on v2=true2025.0472.1MOBILE2025.0471.7RAMBO2025.0468.7COMBO2025.0455.1DQL2025.0447.8CQL2025.0445.3IQL2025.0444.2TD3+BC2025.0443.4MOReL2025.0440.2