Policy learning from action-inclusive feedback on OpenML (K ≥ 3, N ≥ 70,000)
58.41Policy Accuracy
CB Policy
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2022.06 | 58.41 | - | - | |
2022.06 | 50.11 | - | 0.79 | |
2022.06 | 11.91 | - | 0.22 | |
2022.06 | - | 22.57 | - |
CB Policy
| Method | Links | |||
|---|---|---|---|---|
2022.06 | 58.41 | - | - | |
2022.06 | 50.11 | - | 0.79 | |
2022.06 | 11.91 | - | 0.22 | |
2022.06 | - | 22.57 | - |