ResearchBenchmarksOffline Goal-Conditioned Reinforcement Learning on AntMaze Teleport-Stitch v0Offline Goal-Conditioned Reinforcement Learning on AntMaze Teleport-Stitch v0Follow49Success RateIQL15.7224.363341.64Apr 19, 2026Apr 24, 2026Apr 29, 2026May 5, 2026May 10, 2026May 15, 2026May 21, 2026Evaluation resultsMethodMethodLinksSuccess RateIQLSize=1M, Dim.=29Size=1M, Dim.=292026.0549HIQL2vSize=1M, Dim.=29Size=1M, Dim.=292026.0543ARLeSize=1M, Dim.=29Size=1M, Dim.=292026.0541HIQL2vrSize=1M, Dim.=29Size=1M, Dim.=292026.0540GCIVL2026.0439HSVL2026.0438HIQL2026.0436ARLiSize=1M, Dim.=29Size=1M, Dim.=292026.0536GCBC2026.0431CRL2026.0431HIQL1vrSize=1M, Dim.=29Size=1M, Dim.=292026.0529QRL2026.0424GCIQL2026.0417