ResearchBenchmarksOffline Goal-Conditioned Reinforcement Learning on puzzle 3x3 play v0Offline Goal-Conditioned Reinforcement Learning on puzzle 3x3 play v0Follow100Success RateIQL-4235077Apr 19, 2026Apr 24, 2026Apr 29, 2026May 5, 2026May 10, 2026May 15, 2026May 21, 2026Evaluation resultsMethodMethodLinksSuccess RateIQLSize=1M, Dim.=55Size=1M, Dim.=552026.05100GCIQL2026.0495ARLiSize=1M, Dim.=55Size=1M, Dim.=552026.0586HSVL2026.0454ARLeSize=1M, Dim.=55Size=1M, Dim.=552026.0544HIQL1vrSize=1M, Dim.=55Size=1M, Dim.=552026.0527HIQL2vrSize=1M, Dim.=55Size=1M, Dim.=552026.0524HIQL2026.0412GCIVL2026.046CRL2026.043GCBC2026.042QRL2026.041HIQL2vSize=1M, Dim.=55Size=1M, Dim.=552026.050