{"total":33,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"id":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"area":null},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2203.06063","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2111.03917","title":"Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits","created":"2021-11-06","cited_by_count":9,"area":null},{"id":"2210.14322","title":"ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits","created":"2022-10-25","cited_by_count":8,"area":null},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2107.02274","title":"Dueling Bandits with Adversarial Sleeping","created":"2021-07-05","cited_by_count":5,"area":null},{"id":"2202.06694","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2302.06595","title":"When Can We Track Significant Preference Shifts in Dueling Bandits?","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2211.10293","title":"Dueling Bandits: From Two-dueling to Multi-dueling","created":"2022-11-16","cited_by_count":4,"area":null},{"id":"2402.18917","title":"Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization","created":"2024-02-29","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":"2210.14998","title":"One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2209.12108","title":"An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem","created":"2022-09-25","cited_by_count":2,"area":null},{"id":"2403.12950","title":"Non-Stationary Dueling Bandits Under a Weighted Borda Criterion","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2605.08287","title":"Multi-Armed Bandits With Best-Action Queries","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2406.12475","title":"Adversarial Multi-dueling Bandits","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2410.23867","title":"QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2601.07651","title":"Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2111.00870","title":"Statistical Consequences of Dueling Bandits","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2310.00750","title":"Identifying Copeland Winners in Dueling Bandits with Indifferences","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2603.18972","title":"Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.25025","title":"A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.01799","title":"Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}