ResearchBenchmarksOffline Goal-Conditioned Reinforcement Learning on pointmaze giant stitch v0Offline Goal-Conditioned Reinforcement Learning on pointmaze giant stitch v0Follow0Average Binary Success RateIQL-0.001-0.000500.0005May 21, 2026Evaluation resultsMethodMethodLinksAverage Binary Success RateIQLSize=1M, Dim.=2Size=1M, Dim.=22026.050HIQL1vrSize=1M, Dim.=2Size=1M, Dim.=22026.050HIQL2vSize=1M, Dim.=2Size=1M, Dim.=22026.050HIQL2vrSize=1M, Dim.=2Size=1M, Dim.=22026.050ARLiSize=1M, Dim.=2Size=1M, Dim.=22026.050ARLeSize=1M, Dim.=2Size=1M, Dim.=22026.050