Mapping on Mapping H0
4,770.5Mean Episode RewardShared Policy
Evaluation Results
| Method | Links | |
|---|---|---|
| Shared PolicyBudget (B)=200,000, Seeds=52026.04 | 4,770.5 | |
| Local Fine-TuningBudget (B)=200,000, Seeds=52026.04 | 4,763.7 | |
| DC-AdaBudget (B)=200,000, Seeds=52026.04 | 4,757.4 | |
| Obs. NormalizationBudget (B)=200,000, Seeds=52026.04 | 4,715.1 | |
| Random PerturbationBudget (B)=200,000, Seeds=52026.04 | 4,683.9 |