RMAB policy optimization on Food Rescue Notifications N=100, K=50 (real-world)
193.2Normalized RewardLinear-Whittle
Evaluation Results
| Method | Links | |
|---|---|---|
| Linear-Whittle2024.06 | 193.2 | |
| Shapley-Whittle2024.06 | 193.1 | |
| Iterative Linear-Whittle2024.06 | 192.1 | |
| Greedy2024.06 | 182.9 | |
| DQN2024.06 | 154.7 | |
| MCTS2024.06 | 104.7 | |
| Vanilla Whittle2024.06 | 97.5 |