{"total":52,"rows":[{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"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":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"area":null},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"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":"2502.17625","title":"Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"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":"2404.10776","title":"Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback","created":"2024-04-16","cited_by_count":9,"area":"alignment"},{"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":"2311.11185","title":"Dueling Optimization with a Monotone Adversary","created":"2023-11-18","cited_by_count":8,"area":null},{"id":"2510.13907","title":"LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization","created":"2025-10-14","cited_by_count":8,"area":null},{"id":"2202.00935","title":"Non-Stationary Dueling Bandits","created":"2022-02-02","cited_by_count":7,"area":null},{"id":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"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":"2504.12016","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits","created":"2025-04-16","cited_by_count":4,"area":"alignment"},{"id":"2110.03068","title":"Learning the Optimal Recommendation from Explorative Users","created":"2021-10-06","cited_by_count":3,"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":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","cited_by_count":3,"area":"alignment"},{"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":"2405.11204","title":"Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling","created":"2024-05-18","cited_by_count":2,"area":"alignment"},{"id":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2410.05527","title":"DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback","created":"2024-10-07","cited_by_count":2,"area":"alignment"},{"id":"2502.01085","title":"Federated Linear Dueling Bandits","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2602.21585","title":"Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences","created":"2026-02-25","cited_by_count":2,"area":"lr"},{"id":"2405.11226","title":"The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback","created":"2024-05-18","cited_by_count":1,"area":"alignment"},{"id":"2406.12475","title":"Adversarial Multi-dueling Bandits","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2504.15812","title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2510.25811","title":"Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2604.00523","title":"Lipschitz Dueling Bandits over Continuous Action Spaces","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","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":"2311.14003","title":"Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandit","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2602.08244","title":"Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"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":"2605.01961","title":"Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2605.26554","title":"Linear and Neural Dueling Bandits with Delayed Feedback","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"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},{"id":"2610.19804","title":"Efficient contextual partial monitoring with general function approximation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}