ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium-Expert Noise 7Follow97.29Normalized ReturnI-TAP54.847665.866376.88587.9037Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnI-TAPModel Category=Model-B...Model Category=Model-Based2026.0297.29L-MAPModel Category=Model-B...Model Category=Model-Based2026.0293.48CQLModel Category=Model-FreeModel Category=Model-Free2026.0291.44TAPModel Category=Model-B...Model Category=Model-Based2026.0291.4IQLModel Category=Model-FreeModel Category=Model-Free2026.0286.66DTModel Category=Model-FreeModel Category=Model-Free2026.0264.671R2RModel Category=Model-B...Model Category=Model-Based2026.0256.48