ResearchBenchmarksOffline Reinforcement Learning on D4RL ant-expertFollow126.8Normalized ScoreIGDF74.2887.915101.55115.185Dec 2, 2025Evaluation ResultsMethodMethodLinksNormalized ScoreIGDF2025.12126.8DARA2025.12124.5DROCO2025.12120IQL*variant=tuned/reproducedvariant=tuned/reproduced2025.12116.3OTDF2025.12111CQL*variant=tuned/reproducedvariant=tuned/reproduced2025.1294.4BOSA2025.1276.3