Regret Analysis of Retry-Based Bandits
arXiv:2605.20854v3 Announce Type: replace Abstract: We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivat...
arXiv:2605.20854v3 Announce Type: replace Abstract: We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivat...
The paper studies the trade‑off between maximizing rewards and accurately estimating current treatment effects in nonstationary multi‑armed bandits. For $K$‑armed bandits with H"older‑smooth mean rewards, the authors derive minimax bounds on expected dynamic regret under a high‑probability simultaneous coverage requirement for all current effects. They propose the TRACE algorithm, which achieves a regret–precision trade‑off that separates reward‑learning regret from the unavoidable cost of refreshing current‑effect estimates, and extend the method with an empirical‑Bernstein e‑process to adapt exploration while preserving worst‑case guarantees.
The paper presents the first ≥O(ε^{-1}) upper bounds for offline contextual bandits with forward-KL regularization under single-policy concentrability, covering both tabular and general function approximation settings. It introduces a convex-analytical approach that leverages pessimism in a novel way, avoiding previous mean value theorem-based proofs. The authors also provide matching lower bounds, showing the tightness of their rates and that the forward-KL sample complexity reverts to the unregularized slow rate when regularization is weak.
arXiv:2610.08963v1 Announce Type: new Abstract: Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come fr...
Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy. A standard way to balance this trade-off is via a KL-regularized RL objective, although this formulation does not by itself provide a principled way to set the regularization coefficient.
arXiv:2603. 06957v2 Announce Type: replace-cross Abstract: We study post-training linear autoregressive models with outcome and process rewards.
The paper investigates transfer learning in stochastic multi‑armed bandits when historical data come from an unknown adaptive policy. It establishes asymptotic problem‑dependent lower bounds and introduces the KL‑UCB‑Transfer algorithm, which combines online and historical data to achieve logarithmic regret with an improved constant under certain mean‑gap conditions. The study also relaxes the source‑target discrepancy assumption to a one‑sided condition, demonstrating that logarithmic regret can still be achieved under misspecification and identifying regimes of improvement, degradation, or loss of guarantee.
arXiv:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.
arXiv:2607. 26358v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy.
arXiv:2611.05942v1 Announce Type: new Abstract: RL for LLM reasoning often reaches an early performance plateau as the policy distribution becomes increasingly sharp. Recent work has studied policy e...
arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.
arXiv:2605. 20854v2 Announce Type: replace Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$.