Reinforcement Learning on Joint Replenishment 67^20
-3,723.03Mean ReturnCacla, A2C
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Cacla, A2CNum Seeds=102026.02 | -3,723.03 | -3,721.32 | 33.03 | 7 | 0 | |
| DNC (greedy), A2CNum Seeds=102026.02 | -3,742.51 | -3,737.43 | 32.54 | 6 | 0 | |
| DGRL (SDN, DBU)Num Seeds=102026.02 | -3,810.73 | -3,812.63 | 33.26 | 4 | -2 | |
| DNC (SA), A2CNum Seeds=102026.02 | -3,999.4 | -4,011.4 | 166.32 | 0 | -7 |