An explicitly exploratory iterative NLHF method achieves O(sqrt(T)) regret for Nash equilibria under general preference models, removing the exponential KL dependence that plagues standard iterative approaches.
arXiv preprint arXiv:2205.14211 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
citing papers explorer
-
Efficient Exploration for Iterative Nash Preference Optimization
An explicitly exploratory iterative NLHF method achieves O(sqrt(T)) regret for Nash equilibria under general preference models, removing the exponential KL dependence that plagues standard iterative approaches.
-
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.