Image de couverture de livre

Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Levy, Orin, Rosenberg, Aviv, Cohen, Alon, Mansour, Yishay
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Eluder-based Regret for Stochastic Contextual MDPs
par: Levy, Orin, et autres
Publié: (2022)

Optimal Regret for Policy Optimization in Contextual Bandits
par: Levy, Orin, et autres
Publié: (2026)

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
par: Levy, Orin, et autres
Publié: (2025)

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
par: Lancewicki, Tal, et autres
Publié: (2025)

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
par: Cassel, Asaf, et autres
Publié: (2024)

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
par: Cassel, Asaf, et autres
Publié: (2024)

The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
par: Barnea, Idan, et autres
Publié: (2026)

Rate-Optimal Policy Optimization for Linear Markov Decision Processes
par: Sherman, Uri, et autres
Publié: (2023)

Online Weighted Paging with Unknown Weights
par: Levy, Orin, et autres
Publié: (2024)

Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
par: Cassel, Asaf, et autres
Publié: (2024)

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
par: Sherman, Uri, et autres
Publié: (2025)

Regret Guarantees for Linear Contextual Stochastic Shortest Path
par: Polikar, Dor, et autres
Publié: (2025)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
par: Schlisselberg, Ofir, et autres
Publié: (2026)

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization
par: Stradi, Francesco Emanuele, et autres
Publié: (2024)

Individual Regret in Cooperative Stochastic Multi-Armed Bandits
par: Barnea, Idan, et autres
Publié: (2024)

The Sample Complexity of Multiclass and Sparse Contextual Bandits
par: Erez, Liad, et autres
Publié: (2026)

Probably Approximately Precision and Recall Learning
par: Cohen, Lee, et autres
Publié: (2024)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
par: Li, Long-Fei, et autres
Publié: (2024)

Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
par: Bhattacharyya, Riddhiman, et autres
Publié: (2026)

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
par: Schlisselberg, Ofir, et autres
Publié: (2025)

The Real Price of Bandit Information in Multiclass Classification
par: Erez, Liad, et autres
Publié: (2024)

Fast Rates for Bandit PAC Multiclass Classification
par: Erez, Liad, et autres
Publié: (2024)

How to Boost Any Loss Function
par: Nock, Richard, et autres
Publié: (2024)

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
par: Dann, Christoph, et autres
Publié: (2026)

Regret Minimization and Convergence to Equilibria in General-sum Markov Games
par: Erez, Liad, et autres
Publié: (2022)

The Hidden Cost of Approximation in Online Mirror Descent
par: Schlisselberg, Ofir, et autres
Publié: (2025)

Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
par: Ganesh, Swetha, et autres
Publié: (2024)

Rising Rested MAB with Linear Drift
par: Amichay, Omer, et autres
Publié: (2025)

Non-stochastic Bandits With Evolving Observations
par: Bar-On, Yogev, et autres
Publié: (2024)

Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back
par: Cohen, Alon, et autres
Publié: (2025)

Online Set Learning from Precision and Recall Feedback
par: Cohen, Lee, et autres
Publié: (2026)

Delay as Payoff in MAB
par: Schlisselberg, Ofir, et autres
Publié: (2024)

Bayesian Risk-Sensitive Policy Optimization For MDPs With General Loss Functions
par: Wang, Xiaoshuang, et autres
Publié: (2025)

Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
par: Qian, Jian, et autres
Publié: (2024)

Truly No-Regret Learning in Constrained MDPs
par: Müller, Adrian, et autres
Publié: (2024)

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

Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs
par: Zamir, Guy, et autres
Publié: (2026)

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

Learnability Gaps of Strategic Classification
par: Cohen, Lee, et autres
Publié: (2024)

Near-Optimal Sample Complexity for Online Constrained MDPs
par: Liu, Chang, et autres
Publié: (2026)