List your company

Search & Rescue on Search & Rescue H3

16.1Mean Episode RewardShared Policy
13.514.17514.8515.525Apr 5, 2026

Evaluation results

MethodLinks
Shared PolicyBudget (B)=200,000, Seeds=52026.0416.1
Obs. NormalizationBudget (B)=200,000, Seeds=52026.0415.9
DC-AdaBudget (B)=200,000, Seeds=52026.0415.2
Local Fine-TuningBudget (B)=200,000, Seeds=52026.0414.8
Random PerturbationBudget (B)=200,000, Seeds=52026.0413.6