ResearchBenchmarksOffline Reinforcement Learning on D4RL ant-medium-replayFollow69.6Normalized ScoreOTDF11.25626.40341.5556.697Dec 2, 2025Evaluation ResultsMethodMethodLinksNormalized ScoreOTDF2025.1269.6DROCO2025.1266.9DARA2025.1264.1IQL*variant=tuned/reproducedvariant=tuned/reproduced2025.1259.7IGDF2025.1258.2CQL*variant=tuned/reproducedvariant=tuned/reproduced2025.1239.5IQL2025.1229.8IGDF2025.1228.7DVDF-OTDF2025.1227BOSA2025.1224OTDF2025.1220.4BOSA2025.1219.7DVDF-IGDF2025.1219.7DARA2025.1213.5