With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
Online iterative reinforce- ment learning from human feedback with general preference model
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Introduces KL misspecification for bandits and RL under function approximation and proves explicit KL-regret bounds for regression-based Gibbs algorithms that recover the realizable case.
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.
STILL-2 uses imitation of distilled long-form thoughts, multi-rollout exploration on difficult problems, and iterative self-improvement of the dataset to train reasoning models that reach competitive performance on three challenging benchmarks.
citing papers explorer
-
Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
-
Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification
Introduces KL misspecification for bandits and RL under function approximation and proves explicit KL-regret bounds for regression-based Gibbs algorithms that recover the realizable case.
-
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.