Sample Complexity Analysis on Forward KL-regularized Contextual Bandits Function Approximation
2Sample ComplexityForward KL-Regularized RLHF
Evaluation Results
| Method | Links | |
|---|---|---|
| Forward KL-Regularized RLHFType=Upper Bound, Setting=Function Approximation2026.05 | 2 | |
| FKL-PCBType=Upper Bound, Setting=Function Approximation2026.05 | 2 |