ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym MuJoCo walker2d-mediumFollow83.7Normalized ScoreTD3+BC58.11664.75871.478.042Jun 12, 2026Evaluation ResultsMethodMethodLinksNormalized ScoreTD3+BCSeeds=5Seeds=52026.0683.7DRIVESeeds=5Seeds=52026.0681CQLSeeds=5Seeds=52026.0679.2BCSeeds=5Seeds=52026.0678.8IQLSeeds=5Seeds=52026.0678.3DTSeeds=5Seeds=52026.0678.1PDiTSeeds=5Seeds=52026.0677.6BEARSeeds=5Seeds=52026.0659.1