ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium (Noise 0)Offline Reinforcement Learning on Walker2D Medium (Noise 0)Follow79.57Normalized ReturnI-TAP50.637258.148665.6673.1714Feb 21, 2026Evaluation resultsMethodMethodLinksNormalized ReturnI-TAPModel Category=Model-B...Model Category=Model-Based2026.0279.57IQLModel Category=Model-FreeModel Category=Model-Free2026.0278.3L-MAPModel Category=Model-B...Model Category=Model-Based2026.0275.54CQLModel Category=Model-FreeModel Category=Model-Free2026.0272.51R2RModel Category=Model-B...Model Category=Model-Based2026.0255.69DTModel Category=Model-FreeModel Category=Model-Free2026.0255.36TAPModel Category=Model-B...Model Category=Model-Based2026.0251.75