Reinforcement Learning on Recommender hybrid 343
1,579.64Mean ScoreDGRL (SDN, DBU)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DGRL (SDN, DBU)Num Seeds=102026.02 | 1,579.64 | 1,577.34 | 23.34 | 0.11 | 0.17 | |
| Hybrid DNC, H-A2CNum Seeds=102026.02 | 1,362.25 | 1,412.97 | 144.42 | 0 | 0.05 | |
| Hybrid Cacla, DDPGNum Seeds=102026.02 | 1,335.42 | 1,342.34 | 34.54 | -0.04 | 0 |