Imagen de Portada

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Shulun, Zhou, Runlong, Zhang, Zihan, Fazel, Maryam, Du, Simon S.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
por: Chen, Shulun, et al.
Publicado: (2025)

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
por: Li, Mingyi, et al.
Publicado: (2026)

Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback
por: Zhou, Runlong, et al.
Publicado: (2025)

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
por: Shi, Ruizhe, et al.
Publicado: (2025)

Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs
por: Zamir, Guy, et al.
Publicado: (2026)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
por: Boudart, Pierre, et al.
Publicado: (2026)

Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
por: Wang, Zhiyong, et al.
Publicado: (2024)

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

Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
por: Boone, Victor, et al.
Publicado: (2024)

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

Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning
por: Chen, Zijun, et al.
Publicado: (2026)

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures
por: Zhou, Mo, et al.
Publicado: (2025)

Horizon-Free Regret for Linear Markov Decision Processes
por: Zhang, Zihan, et al.
Publicado: (2024)

Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models
por: Xu, Weihang, et al.
Publicado: (2024)

Towards Optimal Differentially Private Regret Bounds in Linear MDPs
por: Sahu, Sharan
Publicado: (2025)

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
por: Cassel, Asaf, et al.
Publicado: (2024)

VASSO: Variance Suppression for Sharpness-Aware Minimization
por: Li, Bingcong, et al.
Publicado: (2025)

Precise Asymptotics and Refined Regret of Variance-Aware UCB
por: Fan, Yingying, et al.
Publicado: (2024)

Truly No-Regret Learning in Constrained MDPs
por: Müller, Adrian, et al.
Publicado: (2024)

Q-Learning with Fine-Grained Gap-Dependent Regret
por: Zhang, Haochen, et al.
Publicado: (2025)

Offline Multi-task Transfer RL with Representational Penalization
por: Bose, Avinandan, et al.
Publicado: (2024)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
por: Li, Long-Fei, et al.
Publicado: (2024)

Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian
por: Zhang, Yiran, et al.
Publicado: (2025)

Solving Robust MDPs through No-Regret Dynamics
por: Guha, Etash Kumar
Publicado: (2023)

Eluder-based Regret for Stochastic Contextual MDPs
por: Levy, Orin, et al.
Publicado: (2022)

No-Regret Reinforcement Learning in Smooth MDPs
por: Maran, Davide, et al.
Publicado: (2024)

Data-Dependent Regret Bounds for Constrained MABs
por: Genalti, Gianmarco, et al.
Publicado: (2025)

Regret Bounds for Noise-Free Cascaded Kernelized Bandits
por: Li, Zihan, et al.
Publicado: (2022)

Learning Optimal Tax Design in Nonatomic Congestion Games
por: Cui, Qiwen, et al.
Publicado: (2024)

Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
por: Zhou, Runlong, et al.
Publicado: (2024)

The Crucial Role of Samplers in Online Direct Preference Optimization
por: Shi, Ruizhe, et al.
Publicado: (2024)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
por: Tsuchiya, Taira, et al.
Publicado: (2025)

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
por: Cassel, Asaf, et al.
Publicado: (2024)

Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference
por: Jamshidi, Fateme, et al.
Publicado: (2025)

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
por: Di Gennaro, Federico, et al.
Publicado: (2025)

Gap-Dependent Bounds for Federated $Q$-learning
por: Zhang, Haochen, et al.
Publicado: (2025)

How Does Variance Shape the Regret in Contextual Bandits?
por: Jia, Zeyu, et al.
Publicado: (2024)

Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling
por: Shah, Mohammad Taha, et al.
Publicado: (2025)

Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
por: Lu, Michael, et al.
Publicado: (2024)

Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
por: Satheesh, Anirudh, et al.
Publicado: (2026)