{"total":118,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"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":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"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":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45,"area":null},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2105.14363","title":"On the Theory of Reinforcement Learning with Once-per-Episode Feedback","created":"2021-05-29","cited_by_count":32,"area":null},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2206.11489","title":"Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation","created":"2022-06-23","cited_by_count":30,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"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":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2207.10786","title":"Delayed Feedback in Generalised Linear Bandits Revisited","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22,"area":null},{"id":"2110.10018","title":"Dynamic pricing and assortment under a contextual MNL demand","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"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":"2507.11847","title":"Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update","created":"2025-07-16","cited_by_count":16,"area":null},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","cited_by_count":15,"area":null},{"id":"2502.10020","title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","created":"2025-02-14","cited_by_count":15,"area":null},{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2103.05750","title":"Regret Bounds for Generalized Linear Bandits under Parameter Drift","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2311.07565","title":"Exploration via linearly perturbed loss minimisation","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","cited_by_count":13,"area":"alignment"},{"id":"2103.11489","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","created":"2021-03-21","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":"2311.04402","title":"Likelihood Ratio Confidence Sets for Sequential Decision Making","created":"2023-11-08","cited_by_count":10,"area":null},{"id":"2405.17061","title":"Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation","created":"2024-05-27","cited_by_count":10,"area":"deeprl"},{"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":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2410.01112","title":"Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7,"area":null},{"id":"2405.20165","title":"Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2024-05-30","cited_by_count":7,"area":"deeprl"},{"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":"2311.08168","title":"Time-Uniform Confidence Spheres for Means of Random Vectors","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2403.04568","title":"Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition","created":"2024-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2403.10738","title":"Horizon-Free Regret for Linear Markov Decision Processes","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2601.01069","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs","created":"2026-01-03","cited_by_count":5,"area":null},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2401.03786","title":"Long-term Safe Reinforcement Learning with Binary Feedback","created":"2024-01-08","cited_by_count":4,"area":"deeprl"},{"id":"2502.01876","title":"Reinforcement Learning with Segment Feedback","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2511.03606","title":"Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2601.19300","title":"Queue Length Regret Bounds for Contextual Queueing Bandits","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2206.00314","title":"Contextual Bandits with Knapsacks for a Conversion Model","created":"2022-06-01","cited_by_count":3,"area":null},{"id":"2402.15171","title":"Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2410.17075","title":"Combinatorial Logistic Bandits","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2501.18282","title":"Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective","created":"2025-01-30","cited_by_count":3,"area":"alignment"},{"id":"2505.18901","title":"PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models","created":"2025-05-24","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":"2507.05306","title":"Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2305.15807","title":"Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2410.20640","title":"Near Optimal Pure Exploration in Logistic Bandits","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2504.02324","title":"Dynamic Assortment Selection and Pricing with Censored Preference Feedback","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.13163","title":"Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","cited_by_count":2,"area":"alignment"},{"id":"2508.03072","title":"Achieving Limited Adaptivity for Multinomial Logistic Bandits","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.06483","title":"A variational approach to dimension-free self-normalized concentration","created":"2025-08-08","cited_by_count":2,"area":null},{"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":"2606.09668","title":"Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2209.07154","title":"Risk-aware linear bandits with convex loss","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2301.00260","title":"Confidence Sets under Generalized Self-Concordance","created":"2022-12-31","cited_by_count":1,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","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":"2412.02861","title":"An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits","created":"2024-12-03","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":"2505.22254","title":"A Unified Online-Offline Framework for Co-Branding Campaign Recommendations","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2505.22820","title":"Preference Learning with Response Time: Robust Losses and Guarantees","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2505.23557","title":"Learning Parametric Distributions from Samples and Preferences","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2507.06859","title":"Episodic Contextual Bandits with Knapsacks under Conversion Models","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.13981","title":"Multi-User Contextual Cascading Bandits for Personalized Recommendation","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2601.20666","title":"Learning Contextual Runtime Monitors for Safe AI-Based Autonomy","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.10971","title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.09448","title":"Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2605.09454","title":"Optimal Regret for Single Index Bandits","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2608.15848","title":"Generalized Linear Bandits with Memory","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2112.06362","title":"Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2212.07632","title":"Reinforcement Learning in Credit Scoring and Underwriting","created":"2022-12-15","cited_by_count":0,"area":null},{"id":"2303.02691","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2410.08578","title":"Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2501.19401","title":"DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits","created":"2025-01-31","cited_by_count":0,"area":null}],"next_cursor":"100"}