Regret Bound Estimation on Hybrid MDPs Bilinear setting
2Off-Policy Regret BoundLiu et al. (2025)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Liu et al. (2025)Model-Free=✗, Bandit Feedback=✓, General Reward=✓2025.10 | 2 | — | |
| Liu et al. (2025)Model-Free=✓, Bandit Feedback=✗, General Reward=✗2025.10 | 5 | 3 | |
| Dig-DECModel-Free=✓, Bandit Feedback=✓, General Reward=✗2025.10 | 13 | 5 |