List your company

Warehouse evaluation on Warehouse H1

270.8Mean Episode RewardObs. Normalization
233.568243.234252.9262.566Apr 5, 2026

Evaluation results

MethodLinks
Obs. NormalizationBudget (B)=200,000, Seeds=52026.04270.8
Shared PolicyBudget (B)=200,000, Seeds=52026.04254.5
DC-AdaBudget (B)=200,000, Seeds=52026.04254.1
Local Fine-TuningBudget (B)=200,000, Seeds=52026.04253.7
Random PerturbationBudget (B)=200,000, Seeds=52026.04235