Warehouse evaluation on Warehouse H1
270.8Mean Episode RewardObs. Normalization
Evaluation Results
| Method | Links | |
|---|---|---|
| Obs. NormalizationBudget (B)=200,000, Seeds=52026.04 | 270.8 | |
| Shared PolicyBudget (B)=200,000, Seeds=52026.04 | 254.5 | |
| DC-AdaBudget (B)=200,000, Seeds=52026.04 | 254.1 | |
| Local Fine-TuningBudget (B)=200,000, Seeds=52026.04 | 253.7 | |
| Random PerturbationBudget (B)=200,000, Seeds=52026.04 | 235 |