{"total":63,"rows":[{"id":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"area":null},{"id":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22,"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":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2205.12086","title":"Information-Directed Selection for Top-Two Algorithms","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2501.17513","title":"Sequential Learning of the Pareto Front for Multi-objective Bandits","created":"2025-01-29","cited_by_count":15,"area":null},{"id":"2210.00974","title":"Dealing with Unknown Variances in Best-Arm Identification","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2402.16710","title":"Cost Aware Best Arm Identification","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","cited_by_count":12,"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":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2210.05431","title":"Non-Asymptotic Analysis of a UCB-based Top Two Algorithm","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2306.12774","title":"Pure Exploration in Bandits with Linear Constraints","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2406.03033","title":"Optimal Multi-Fidelity Best-Arm Identification","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2106.14077","title":"The Role of Contextual Information in Best Arm Identification","created":"2021-06-26","cited_by_count":8,"area":null},{"id":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","cited_by_count":8,"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":"2210.00895","title":"On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits","created":"2022-09-30","cited_by_count":8,"area":null},{"id":"2306.09048","title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2310.14129","title":"Optimal Batched Best Arm Identification","created":"2023-10-21","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":"2409.05072","title":"A General Framework for Clustering and Distribution Matching with Bandit Feedback","created":"2024-09-08","cited_by_count":7,"area":null},{"id":"2202.06280","title":"On the complexity of All $\\varepsilon$-Best Arms Identification","created":"2022-02-13","cited_by_count":6,"area":null},{"id":"2309.02202","title":"On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence","created":"2023-09-05","cited_by_count":6,"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":"2405.11548","title":"Adaptive Online Experimental Design for Causal Discovery","created":"2024-05-19","cited_by_count":5,"area":null},{"id":"2409.18909","title":"Best Arm Identification with Minimal Regret","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2201.04469","title":"Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2310.00539","title":"Thompson Exploration with Best Challenger Rule in Best Arm Identification","created":"2023-10-01","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":"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":"2207.11158","title":"SPRT-based Efficient Best Arm Identification in Stochastic Bandits","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2209.07330","title":"Best Arm Identification with Contextual Information under a Small Gap","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2308.00978","title":"Certified Multi-Fidelity Zeroth-Order Optimization","created":"2023-08-02","cited_by_count":3,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","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":"2301.03785","title":"Best Arm Identification in Stochastic Bandits: Beyond $\\beta-$optimality","created":"2023-01-10","cited_by_count":2,"area":null},{"id":"2502.04021","title":"Variational Quantum Optimization with Continuous Bandits","created":"2025-02-06","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":"2607.04824","title":"Probably Correct Optimal Stable Matching under Two-Sided Uncertainty","created":"2026-07-06","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":"2308.15552","title":"Pure Exploration under Mediators' Feedback","created":"2023-08-29","cited_by_count":1,"area":"alignment"},{"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":"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":"2606.01708","title":"Two-Fidelity Best-Action Identification for Stochastic Minimax Tree","created":"2026-06-01","cited_by_count":1,"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":"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":"2607.08979","title":"Optimal Top-$k$ Identification from Pairwise Comparisons","created":"2026-07-09","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":"2609.32165","title":"FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33132","title":"Quantum Monte Carlo Tree Search with Fixed Confidence","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33986","title":"ICMAPE: In-Context Multiagent Pure Exploration","created":"2026-09-27","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}