ResearchBenchmarksOffline Reinforcement Learning on Walker2D Medium Noise 12Follow61.49Normalized ReturnCQL30.955638.882846.8154.7372Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnCQLModel Category=Model-FreeModel Category=Model-Free2026.0261.49I-TAPModel Category=Model-B...Model Category=Model-Based2026.0260.35L-MAPModel Category=Model-B...Model Category=Model-Based2026.0259.05TAPModel Category=Model-B...Model Category=Model-Based2026.0252.2IQLModel Category=Model-FreeModel Category=Model-Free2026.0247.53DTModel Category=Model-FreeModel Category=Model-Free2026.0232.21R2RModel Category=Model-B...Model Category=Model-Based2026.0232.13