Image de couverture de livre

Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Kihyun, Baek, Beomhan, Lee, Dabeen
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
par: Yu, Kihyun, et autres
Publié: (2026)

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
par: Yu, Kihyun, et autres
Publié: (2024)

Provably Efficient Infinite-Horizon Average-Reward Reinforcement Learning with Linear Function Approximation
par: Chae, Woojin, et autres
Publié: (2024)

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span
par: Chae, Woojin, et autres
Publié: (2024)

On Convergence of Average-Reward Q-Learning in Weakly Communicating Markov Decision Processes
par: Wan, Yi, et autres
Publié: (2024)

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
par: Baek, Beomhan, et autres
Publié: (2025)

Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
par: Yu, Kihyun, et autres
Publié: (2026)

Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributions
par: Park, Sungwoo, et autres
Publié: (2024)

Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
par: Boone, Victor, et autres
Publié: (2024)

Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
par: Song, Minhak, et autres
Publié: (2025)

Stochastic-Constrained Stochastic Optimization with Markovian Data
par: Kim, Yeongjong, et autres
Publié: (2023)

Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation
par: Park, Jaehyun, et autres
Publié: (2024)

Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
par: Zurek, Matthew, et autres
Publié: (2024)

Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
par: Yoon, Hoyeol, et autres
Publié: (2026)

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
par: Chen, Zijun, et autres
Publié: (2025)

Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
par: Kaya, Ege C., et autres
Publié: (2026)

Optimal Sample Complexity for Average Reward Markov Decision Processes
par: Wang, Shengbo, et autres
Publié: (2023)

Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
par: Wang, Shengbo, et autres
Publié: (2026)

Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain
par: Wang, Shengbo, et autres
Publié: (2025)

Tail Distribution of Regret in Optimistic Reinforcement Learning
par: Khodadadian, Sajad, et autres
Publié: (2025)

Reinforcement Learning and Regret Bounds for Admission Control
par: Weber, Lucas, et autres
Publié: (2024)

Learning Decentralized Linear Quadratic Regulators with $\sqrt{T}$ Regret
par: Ye, Lintao, et autres
Publié: (2022)

Probabilistic Safety Guarantee for Stochastic Control Systems Using Average Reward MDPs
par: Omidi, Saber, et autres
Publié: (2025)

Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems
par: Ziemann, Ingvar, et autres
Publié: (2022)

Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization
par: Zhao, Peng, et autres
Publié: (2025)

Span-Based Optimal Sample Complexity for Average Reward MDPs
par: Zurek, Matthew, et autres
Publié: (2023)

Robust Regression over Averaged Uncertainty
par: Bertsimas, Dimitris, et autres
Publié: (2023)

Regret of exploratory policy improvement and $q$-learning
par: Tang, Wenpin, et autres
Publié: (2024)

Planning and Learning in Average Risk-aware MDPs
par: Wang, Weikai, et autres
Publié: (2025)

Wasserstein Distributionally Robust Regret Optimization
par: Fiechtner, Lukas-Benedikt, et autres
Publié: (2025)

Rethinking PCA Through Duality
par: Quan, Jan, et autres
Publié: (2025)

Regret Analysis: a control perspective
par: Gibson, Travis E., et autres
Publié: (2025)

Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback
par: Ba, Wenjia, et autres
Publié: (2021)

Rate-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator
par: Hutchinson, Spencer, et autres
Publié: (2026)

Lagrangian Index Policy for Restless Bandits with Average Reward
par: Avrachenkov, Konstantin, et autres
Publié: (2024)

Central Limit Theorems for Asynchronous Averaged Q-Learning
par: Liu, Xingtu
Publié: (2025)

Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning
par: Li, Zihao, et autres
Publié: (2024)

An Equivalence Between Static and Dynamic Regret Minimization
par: Jacobsen, Andrew, et autres
Publié: (2024)

Federated ADMM from Bayesian Duality
par: Möllenhoff, Thomas, et autres
Publié: (2025)

The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
par: Zurek, Matthew, et autres
Publié: (2024)