Reinforcement Learning on Job Shop Scheduling 10^10
-39.79Mean Completion TimeDNC (SA), A2C
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DNC (SA), A2CNum Seeds=102026.02 | -39.79 | 0.58 | 121.52 | 0 | -99 | |
| DNC (greedy), A2CNum Seeds=102026.02 | 1,607.34 | 1,711.94 | 1,186.28 | 293,993 | 19 | |
| Cacla, A2CNum Seeds=102026.02 | 2,110.37 | 1,433.98 | 1,545.78 | 246,242 | 0 | |
| DGRL (SDN, DBU)Num Seeds=102026.02 | 4,027.51 | 4,033.32 | 227.08 | 692,782 | 181 |