ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium-Replay Noise 0Follow90.67Normalized Return1R2R46.750858.152969.55580.9571Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized Return1R2RModel Category=Model-B...Model Category=Model-Based2026.0290.67CQLModel Category=Model-FreeModel Category=Model-Free2026.0277.2IQLModel Category=Model-FreeModel Category=Model-Free2026.0277.2I-TAPModel Category=Model-B...Model Category=Model-Based2026.0275.49TAPModel Category=Model-B...Model Category=Model-Based2026.0272.32L-MAPModel Category=Model-B...Model Category=Model-Based2026.0270.66DTModel Category=Model-FreeModel Category=Model-Free2026.0248.44