ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium (Noise 7)Follow65.85Normalized ReturnI-TAP42.886848.848454.8160.7716Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnI-TAPModel Category=Model-B...Model Category=Model-Based2026.0265.851R2RModel Category=Model-B...Model Category=Model-Based2026.0265.16L-MAPModel Category=Model-B...Model Category=Model-Based2026.0262.23CQLModel Category=Model-FreeModel Category=Model-Free2026.0249.38IQLModel Category=Model-FreeModel Category=Model-Free2026.0248.82TAPModel Category=Model-B...Model Category=Model-Based2026.0244.46DTModel Category=Model-FreeModel Category=Model-Free2026.0243.77