{"total":25,"rows":[{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16,"area":null},{"id":"2402.14987","title":"On the Performance of Empirical Risk Minimization with Smoothed Data","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2402.18591","title":"Stochastic contextual bandits with graph feedback: from independence number to MAS number","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2502.05974","title":"Decision Making in Hybrid Environments: A Model Aggregation Approach","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2410.09597","title":"A Complete Characterization of Learnability for Stochastic Noisy Bandits","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2503.00273","title":"Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2506.14746","title":"On the Hardness of Bandit Learning","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2510.08882","title":"An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2606.07931","title":"Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2404.09123","title":"Provable Interactive Learning with Hindsight Instruction Feedback","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2605.29645","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.11171","title":"Bellman-sufficient Information Complexity","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2303.03327","title":"Tight Bounds for $\\gamma$-Regret via the Decision-Estimation Coefficient","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2407.13622","title":"Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2502.14790","title":"Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2605.09200","title":"A Complete Characterization of Learnability for Adversarial Noisy Bandits","created":"2026-05-09","cited_by_count":0,"area":null}],"next_cursor":null}