Cover Image

Logarithmic Regret for Online KL-Regularized Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Heyang, Ye, Chenlu, Xiong, Wei, Gu, Quanquan, Zhang, Tong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
by: Zhao, Heyang, et al.
Published: (2024)

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
by: Ji, Kaixuan, et al.
Published: (2026)

Corruption-Robust Offline Reinforcement Learning with General Function Approximation
by: Ye, Chenlu, et al.
Published: (2023)

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
by: Ye, Chenlu, et al.
Published: (2024)

Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
by: Ye, Chenlu, et al.
Published: (2022)

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
by: Zhao, Qingyue, et al.
Published: (2026)

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
by: Ji, Kaixuan, et al.
Published: (2026)

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
by: Zhao, Heyang, et al.
Published: (2023)

Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits
by: Zhao, Qingyue, et al.
Published: (2025)

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
by: Nayak, Anupam, et al.
Published: (2025)

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
by: Di, Qiwei, et al.
Published: (2023)

Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
by: Ye, Chenlu, et al.
Published: (2024)

Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
by: Di, Qiwei, et al.
Published: (2023)

Feel-Good Thompson Sampling for Contextual Dueling Bandits
by: Li, Xuheng, et al.
Published: (2024)

Variance-Dependent Regret Lower Bounds for Contextual Bandits
by: He, Jiafan, et al.
Published: (2025)

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint
by: Xiong, Wei, et al.
Published: (2023)

Achieving Constant Regret in Linear Markov Decision Processes
by: Zhang, Weitong, et al.
Published: (2024)

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
by: Di, Qiwei, et al.
Published: (2024)

Energy-Weighted Flow Matching for Offline Reinforcement Learning
by: Zhang, Shiyuan, et al.
Published: (2025)

Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling
by: Di, Qiwei, et al.
Published: (2025)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
by: Zhang, Yifan, et al.
Published: (2025)

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
by: Tsuchiya, Taira, et al.
Published: (2024)

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
by: Zhao, Heyang, et al.
Published: (2025)

Logarithmic Regret for Nonlinear Control
by: Wang, James, et al.
Published: (2025)

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
by: Zhang, Shiyuan, et al.
Published: (2026)

KL-Regularized Reinforcement Learning is Designed to Mode Collapse
by: GX-Chen, Anthony, et al.
Published: (2025)

Model-free Online Learning for the Kalman Filter: Forgetting Factor and Logarithmic Regret
by: Qian, Jiachen, et al.
Published: (2025)

Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction
by: Qian, Jiachen, et al.
Published: (2025)

Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
by: Pai, Chih-Fan, et al.
Published: (2026)

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
by: Zhong, Han, et al.
Published: (2023)

Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
by: Sakaue, Shinsaku, et al.
Published: (2025)

An Online Gradient-Based Caching Policy with Logarithmic Complexity and Regret Guarantees
by: Carra, Damiano, et al.
Published: (2024)

Self-rewarding correction for mathematical reasoning
by: Xiong, Wei, et al.
Published: (2025)

Gradient-Variation Regret Bounds for Unconstrained Online Learning
by: Zhao, Yuheng, et al.
Published: (2026)

Finite-Time Logarithmic Bayes Regret Upper Bounds
by: Atsidakou, Alexia, et al.
Published: (2023)

Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
by: Zheng, Zhong, et al.
Published: (2024)

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
by: Zhang, Chenyang, et al.
Published: (2026)

Reinforcement Learning from Human Feedback with Active Queries
by: Ji, Kaixuan, et al.
Published: (2024)

Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
by: Ye, Chenlu, et al.
Published: (2025)

Degeneracy is OK: Logarithmic Regret for Network Revenue Management with Indiscrete Distributions
by: Jiang, Jiashuo, et al.
Published: (2022)