Inventory Management on Seasonal distribution demand A = 0.9, epsilon = 9
24,610Average RewardHybrid A3C-DPPO
Evaluation Results
| Method | Links | |
|---|---|---|
| Hybrid A3C-DPPOTarget fill rate (beta_k,min)=0.852026.06 | 24,610 | |
| Hybrid A3C-DPPOTarget fill rate (beta_k,min)=0.902026.06 | 22,000 | |
| Hybrid A3C-DPPOTarget fill rate (beta_k,min)=0.952026.06 | 19,833 | |
| PPOTarget fill rate (beta_k,min)=0.992026.06 | 18,800 | |
| PPOTarget fill rate (beta_k,min)=0.852026.06 | 18,400 | |
| Hybrid A3C-DPPOTarget fill rate (beta_k,min)=0.992026.06 | 16,890 | |
| PPOTarget fill rate (beta_k,min)=0.902026.06 | 15,000 | |
| DQNTarget fill rate (beta_k,min)=0.852026.06 | 14,700 | |
| PPOTarget fill rate (beta_k,min)=0.952026.06 | 14,700 | |
| DQNTarget fill rate (beta_k,min)=0.902026.06 | 12,700 | |
| DQNTarget fill rate (beta_k,min)=0.952026.06 | 10,500 | |
| DQNTarget fill rate (beta_k,min)=0.992026.06 | 8,300 | |
| (s,S)Target fill rate (beta_k,min)=0.852026.06 | 5,500 | |
| (s,S)Target fill rate (beta_k,min)=0.902026.06 | 5,500 | |
| (s,S)Target fill rate (beta_k,min)=0.952026.06 | 3,800 | |
| (s,S)Target fill rate (beta_k,min)=0.992026.06 | 2,700 |