ResearchBenchmarksOffline Reinforcement Learning on Mean Medium-ExpertFollow98.5Normalized ReturnI-TAP49.72462.38775.0587.713Feb 21, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnI-TAPModel Category=Model-B...Model Category=Model-Based2026.0298.5CQLModel Category=Model-FreeModel Category=Model-Free2026.0293.84L-MAPModel Category=Model-B...Model Category=Model-Based2026.0293.04IQLModel Category=Model-FreeModel Category=Model-Free2026.0276.97TAPModel Category=Model-B...Model Category=Model-Based2026.0275.26DTModel Category=Model-FreeModel Category=Model-Free2026.0269.851R2RModel Category=Model-B...Model Category=Model-Based2026.0251.6