ResearchBenchmarksOffline Goal-Conditioned Reinforcement Learning on AntMaze Giant-Stitch v0Offline Goal-Conditioned Reinforcement Learning on AntMaze Giant-Stitch v0Follow32Success RateARLi-1.287.361624.64Apr 19, 2026Apr 24, 2026Apr 29, 2026May 5, 2026May 10, 2026May 15, 2026May 21, 2026Evaluation resultsMethodMethodLinksSuccess RateARLiSize=1M, Dim.=29Size=1M, Dim.=292026.0532ARLeSize=1M, Dim.=29Size=1M, Dim.=292026.0521HIQL2vrSize=1M, Dim.=29Size=1M, Dim.=292026.0520HIQL2vSize=1M, Dim.=29Size=1M, Dim.=292026.0515HIQL1vrSize=1M, Dim.=29Size=1M, Dim.=292026.057HIQL2026.042GCBC2026.040GCIVL2026.040GCIQL2026.040QRL2026.040CRL2026.040HSVL2026.040IQLSize=1M, Dim.=29Size=1M, Dim.=292026.050