ResearchBenchmarksMeta-Reinforcement Learning on Point-Robot-Sparse (ID)Meta-Reinforcement Learning on Point-Robot-Sparse (ID)Follow36Average ReturnMetaSTAR0.649.821928.18May 30, 2026Evaluation resultsMethodMethodLinksAverage ReturnMetaSTAREpisode=FinalEpisode=Final2026.0536CORROEpisode=FinalEpisode=Final2026.0517FOCALEpisode=FinalEpisode=Final2026.055UNICORNEpisode=FinalEpisode=Final2026.054CSROEpisode=FinalEpisode=Final2026.052