POMDP Planning on Rearrange(7,4)
6.8ReturnsGammaZero
Evaluation Results
| Method | Links | |
|---|---|---|
| GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=Full search2025.10 | 6.8 | |
| AdaOPSEvaluation Protocol=per-size reference2025.10 | 4 | |
| GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=One-step look-ahead value network (V*θ)2025.10 | 3.8 | |
| GammaZeroEvaluation Protocol=zero-shot transfer, Search Configuration=Raw policy network (Pθ)2025.10 | 3.2 | |
| POMCPOWEvaluation Protocol=per-size reference2025.10 | 0 | |
| DESPOTEvaluation Protocol=per-size reference2025.10 | 0 |