RMAB Policy Optimization on Food Rescue Phone Calls N=20, K=10 (real-world)
129.4Normalized RewardIterative Shapley-Whittle
Evaluation Results
| Method | Links | |
|---|---|---|
| Iterative Shapley-Whittle2024.06 | 129.4 | |
| MCTS Shapley-Whittle2024.06 | 129.3 | |
| MCTS Linear-Whittle2024.06 | 129.1 | |
| Shapley-Whittle2024.06 | 129 | |
| Linear-Whittle2024.06 | 128.8 | |
| Iterative Linear-Whittle2024.06 | 128.7 | |
| Greedy2024.06 | 122.8 | |
| DQN2024.06 | 120.9 | |
| MCTS2024.06 | 107 | |
| Vanilla Whittle2024.06 | 98.9 |