{"total":21,"rows":[{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82,"area":null},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2112.06008","title":"Privacy Amplification via Shuffling for Linear Contextual Bandits","created":"2021-12-11","cited_by_count":17,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2306.05275","title":"Federated Linear Contextual Bandits with User-level Differential Privacy","created":"2023-06-08","cited_by_count":12,"area":null},{"id":"2406.11316","title":"Improved Algorithms for Contextual Dynamic Pricing","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2311.04402","title":"Likelihood Ratio Confidence Sets for Sequential Decision Making","created":"2023-11-08","cited_by_count":10,"area":null},{"id":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2110.11202","title":"Anti-Concentrated Confidence Bonuses for Scalable Exploration","created":"2021-10-21","cited_by_count":7,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2309.13896","title":"Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2102.07987","title":"The Elliptical Potential Lemma for General Distributions with an Application to Linear Thompson Sampling","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2601.02022","title":"Prior Diffusiveness and Regret in the Linear-Gaussian Bandit","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2605.28290","title":"Adaptive Bandit Algorithms for Contextual Matching Markets","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2310.10107","title":"Posterior Sampling-based Online Learning for Episodic POMDPs","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2503.02043","title":"Constrained Linear Thompson Sampling","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2604.08149","title":"A Direct Approach for Handling Contextual Bandits with Latent State Dynamics","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}