{"total":60,"rows":[{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2101.08534","title":"Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback","created":"2021-01-21","cited_by_count":21,"area":null},{"id":"2303.09468","title":"On the Existence of a Complexity in Fixed Budget Bandit Identification","created":"2023-03-16","cited_by_count":20,"area":null},{"id":"2110.15573","title":"A/B/n Testing with Control in the Presence of Subpopulations","created":"2021-10-29","cited_by_count":17,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2205.12086","title":"Information-Directed Selection for Top-Two Algorithms","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2307.00424","title":"Adaptive Algorithms for Relaxed Pareto Set Identification","created":"2023-07-01","cited_by_count":15,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2312.12137","title":"Best Arm Identification with Fixed Budget: A Large Deviation Perspective","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2103.10070","title":"Top-m identification for linear bandits","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2406.03033","title":"Optimal Multi-Fidelity Best-Arm Identification","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2205.10936","title":"On Elimination Strategies for Bandit Fixed-Confidence Identification","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2304.04091","title":"Best Arm Identification with Fairness Constraints on Subpopulations","created":"2023-04-08","cited_by_count":8,"area":null},{"id":"2105.12978","title":"A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits","created":"2021-05-27","cited_by_count":7,"area":null},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2402.01400","title":"Query-Efficient Correlation Clustering with Noisy Oracle","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2310.10359","title":"An Anytime Algorithm for Good Arm Identification","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2411.01898","title":"Best-Arm Identification in Unimodal Bandits","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2410.15564","title":"Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2412.02988","title":"Preference-based Pure Exploration","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2503.07824","title":"Pure Exploration with Feedback Graphs","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2110.09133","title":"Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2204.06910","title":"Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2310.13393","title":"Optimal Best Arm Identification with Fixed Confidence in Restless Bandits","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2406.15648","title":"Testing the Feasibility of Linear Programs with Bandit Feedback","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2502.01425","title":"The Batch Complexity of Bandit Pure Exploration","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2503.09226","title":"Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2208.05844","title":"Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions","created":"2022-08-11","cited_by_count":2,"area":null},{"id":"2408.14195","title":"Representative Arm Identification: A fixed confidence approach to identify cluster representatives","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.15643","title":"Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.17869","title":"Best Group Identification in Multi-Objective Bandits","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.08127","title":"Constrained Pareto Set Identification with Bandit Feedback","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2206.04456","title":"Choosing Answers in $\\varepsilon$-Best-Answer Identification for Linear Bandits","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2505.22473","title":"Pure Exploration with Infinite Answers","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2505.22475","title":"Non-Asymptotic Analysis of (Sticky) Track-and-Stop","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.03062","title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.06978","title":"Near Optimal Non-asymptotic Sample Complexity of 1-Identification","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2507.08994","title":"Fixed-Confidence Multiple Change Point Identification under Bandit Feedback","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2509.19901","title":"Pure Exploration via Frank-Wolfe Self-Play","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.09808","title":"Constrained Best Arm Identification with Tests for Feasibility","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2212.13157","title":"Gaussian Process Classification Bandits","created":"2022-12-26","cited_by_count":0,"area":null},{"id":"2302.02033","title":"An Asymptotically Optimal Algorithm for the Convex Hull Membership Problem","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2402.09467","title":"Optimal Thresholding Linear Bandit","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2505.10147","title":"Near Optimal Best Arm Identification for Clustered Bandits","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2601.22600","title":"An Efficient Algorithm for Thresholding Monte Carlo Tree Search","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.11324","title":"$\\varepsilon$-Good Action Identification in Fixed-Budget Monte Carlo Tree Search","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.21889","title":"Ranking-and-Selection with Multiple Correct Answers and Non-Answerable Estimates","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.02267","title":"Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.13703","title":"Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.19963","title":"Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.38659","title":"Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.16840","title":"Few-for-Many Best-Arm Identification in Multi-Objective Bandits","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18577","title":"When More Objectives Make Identification Easier: The Role of Preferences and Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}