ResearchBenchmarksOffline Goal-Conditioned Reinforcement Learning on AntMaze Giant-Navigate v0Offline Goal-Conditioned Reinforcement Learning on AntMaze Giant-Navigate v0Follow74Success RateHSVL-2.9617.023756.98Apr 19, 2026Apr 24, 2026Apr 29, 2026May 5, 2026May 10, 2026May 15, 2026May 21, 2026Evaluation resultsMethodMethodLinksSuccess RateHSVL2026.0474HIQL2026.0465HIQL2vrSize=1M, Dim.=29Size=1M, Dim.=292026.0548ARLiSize=1M, Dim.=29Size=1M, Dim.=292026.0548ARLeSize=1M, Dim.=29Size=1M, Dim.=292026.0542HIQL2vSize=1M, Dim.=29Size=1M, Dim.=292026.0540HIQL1vrSize=1M, Dim.=29Size=1M, Dim.=292026.0538CRL2026.0416QRL2026.0414GCBC2026.040GCIVL2026.040GCIQL2026.040IQLSize=1M, Dim.=29Size=1M, Dim.=292026.050