Reinforcement Learning on Recommender hybrid 343^10
2,262.56Mean ReturnDGRL (SDN, DBU)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DGRL (SDN, DBU)Num Seeds=102026.02 | 2,262.56 | 2,258.83 | 60.81 | 129 | 29 | |
| Hybrid Cacla, DDPGNum Seeds=102026.02 | 1,740.56 | 1,748.69 | 43.23 | 77 | 0 | |
| Hybrid DNC, H-A2CNum Seeds=102026.02 | 1,011.78 | 982.57 | 112.17 | 0 | -43 |