ResearchBenchmarksPOMDP Planning on Rearrange (5, 2)Follow12.5ReturnGammaZero3.0365.4937.9510.407Oct 15, 2025Evaluation ResultsMethodMethodLinksReturnGammaZeroEvaluation Mode=FullEvaluation Mode=Full2025.1012.5AdaOPSEvaluation Mode=StandardEvaluation Mode=Standard2025.107.7GammaZeroEvaluation Mode=Raw V*θEvaluation Mode=Raw V*θ2025.106.3GammaZeroEvaluation Mode=Raw PθEvaluation Mode=Raw Pθ2025.105.6POMCPOWEvaluation Mode=StandardEvaluation Mode=Standard2025.104.3DESPOTEvaluation Mode=StandardEvaluation Mode=Standard2025.103.4