ResearchBenchmarksOffline Reinforcement Learning on Mean Medium-ReplayFollow76.45Normalized ReturnI-TAP40.122849.553958.98568.4161Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnI-TAPModel Category=Model-B...Model Category=Model-Based2026.0276.45L-MAPModel Category=Model-B...Model Category=Model-Based2026.0270.731R2RModel Category=Model-B...Model Category=Model-Based2026.0264.88CQLModel Category=Model-FreeModel Category=Model-Free2026.0259.17IQLModel Category=Model-FreeModel Category=Model-Free2026.0258.37TAPModel Category=Model-B...Model Category=Model-Based2026.0256.45DTModel Category=Model-FreeModel Category=Model-Free2026.0241.52