Mapping on Mapping H3
4,784Mean Episode RewardShared Policy
Evaluation Results
| Method | Links | |
|---|---|---|
| Shared PolicyBudget (B)=200,000, Seeds=52026.04 | 4,784 | |
| Local Fine-TuningBudget (B)=200,000, Seeds=52026.04 | 4,781.3 | |
| DC-AdaBudget (B)=200,000, Seeds=52026.04 | 4,721.8 | |
| Obs. NormalizationBudget (B)=200,000, Seeds=52026.04 | 4,694.6 | |
| Random PerturbationBudget (B)=200,000, Seeds=52026.04 | 4,689.2 |