List your company

Warehouse on Warehouse H2

269.7Mean Episode RewardObs. Normalization
232.884242.442252261.558Apr 5, 2026

Evaluation results

MethodLinks
Obs. NormalizationBudget (B)=200,000, Seeds=52026.04269.7
DC-AdaBudget (B)=200,000, Seeds=52026.04253.9
Shared PolicyBudget (B)=200,000, Seeds=52026.04253.5
Local Fine-TuningBudget (B)=200,000, Seeds=52026.04252.4
Random PerturbationBudget (B)=200,000, Seeds=52026.04234.3