{"total":62,"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":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"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":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"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":"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":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2202.11795","title":"Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","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":"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":"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":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2306.02628","title":"Active Ranking of Experts Based on their Performances in Many Tasks","created":"2023-06-05","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":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2504.12016","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits","created":"2025-04-16","cited_by_count":4,"area":"alignment"},{"id":"2202.01879","title":"Learning from a Learning User for Optimal Recommendations","created":"2022-02-03","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":"2305.16074","title":"Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2312.11788","title":"Faster Convergence with Multiway Preferences","created":"2023-12-19","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":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2505.23673","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","created":"2025-05-29","cited_by_count":3,"area":"alignment"},{"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":"2407.01887","title":"Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents","created":"2024-07-02","cited_by_count":2,"area":"agents"},{"id":"2502.01085","title":"Federated Linear Dueling Bandits","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2503.11209","title":"Clustering Items through Bandit Feedback: Finding the Right Feature out of Many","created":"2025-03-14","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":"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":"2608.15050","title":"Online Convex Optimization with Dueling Feedback","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2103.02741","title":"Combinatorial Bandits without Total Order for Arms","created":"2021-03-03","cited_by_count":1,"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":"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":"2504.15812","title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","created":"2025-04-22","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":"2101.10670","title":"Ordinal Monte Carlo Tree Search","created":"2021-01-26","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":"2508.05367","title":"Latent Preference Bandits","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2512.14263","title":"DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.22552","title":"Computing Pure-Strategy Nash Equilibria in a Two-Party Policy Competition: Existence and Algorithmic Approaches","created":"2025-12-27","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":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","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":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}