Offline Reinforcement Learning on Theoretical Offline RL
-3Sample ComplexitySidford et al.
Evaluation results
| Method | Links | |
|---|---|---|
| Sidford et al.Finite/Continuous=Finite, Dimension=One, Private=X, One-Sided=X2026.05 | -3 | |
| Qiao and WangFinite/Continuous=Finite, Dimension=One, Private=✓, One-Sided=X2026.05 | 1 | |
| POOLFinite/Continuous=Continuous, Dimension=Multi, Private=✓, One-Sided=✓2026.05 | 1 | |
| Qin et al.Finite/Continuous=Continuous, Dimension=One, Private=X, One-Sided=✓2026.05 | 3 |