Reinforcement Learning on Recommender discrete
2,009.88Mean ScoreDGRL (SDN, DBU)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DGRL (SDN, DBU)Num Seeds=102026.02 | 2,009.88 | 2,006.62 | 42.18 | 31 | 60 | |
| DNC (greedy)Base Algorithm=A2C, Num Seeds=102026.02 | 1,587.59 | 1,637.68 | 273.37 | 7 | 30 | |
| DNC (SA)Base Algorithm=A2C, Num Seeds=102026.02 | 1,534.94 | 1,524.49 | 265.15 | 0 | 21 | |
| CaclaBase Algorithm=A2C, Num Seeds=102026.02 | 1,370.89 | 1,253.92 | 320.12 | -17 | 0 | |
| VACBase Algorithm=A2C, Num Seeds=102026.02 | 826.41 | 876.02 | 152.6 | -42 | -30 | |
| WolpertingerBase Algorithm=DDPG, Num Seeds=102026.02 | 460.38 | 444.65 | 29.42 | -70 | -64 |