List your company

POMDP Planning on LightDark 10

17.5ReturnGammaZero
0.05924.58719.11513.6429Oct 15, 2025

Evaluation results

MethodLinks
GammaZeroEvaluation Mode=Full2025.1017.5
BetaZeroEvaluation Mode=Full2025.1016.17
GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=Full search2025.1015.2
GammaZeroEvaluation Mode=Raw Pθ2025.1014.4
BetaZeroEvaluation Mode=Raw Pθ2025.1013.98
GammaZeroEvaluation Mode=Raw V*θ2025.1013.3
BetaZeroEvaluation Mode=Raw V*θ2025.1012.45
GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=Raw policy network (Pθ)2025.1012.1
GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=One-step look-ahead value network (V*θ)2025.1011.2
AdaOPSEvaluation Mode=Standard2025.106.28
AdaOPSEvaluation Protocol=per-size reference2025.106.28
POMCPOWEvaluation Mode=Standard2025.101.08
POMCPOWEvaluation Protocol=per-size reference2025.101.08
DESPOTEvaluation Mode=Standard2025.100.73
DESPOTEvaluation Protocol=per-size reference2025.100.73