Reinforcement Learning on Recommender 343^10 discrete
1,937.61Mean ReturnDGRL (SDN, DBU)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DGRL (SDN, DBU)Num Seeds=102026.02 | 1,937.61 | 1,941.89 | 53.86 | 147 | 164 | |
| DNC (SA)Base Algorithm=A2C, Num Seeds=102026.02 | 802.8 | 783.96 | 49.54 | 0 | 6 | |
| CaclaBase Algorithm=A2C, Num Seeds=102026.02 | 730.68 | 732.85 | 15.27 | -6 | 0 | |
| DNC (greedy)Base Algorithm=A2C, Num Seeds=102026.02 | 730.46 | 730.52 | 15.86 | -6 | 0 |