{"total":52,"rows":[{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57,"area":null},{"id":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"area":"alignment"},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40,"area":null},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"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":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2502.06363","title":"Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2306.06836","title":"Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds","created":"2023-06-12","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11,"area":"deeprl"},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2303.05606","title":"Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2303.10165","title":"Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","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":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"id":"2305.07911","title":"Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2402.07341","title":"Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2403.10738","title":"Horizon-Free Regret for Linear Markov Decision Processes","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2407.03065","title":"Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes","created":"2024-07-03","cited_by_count":5,"area":"deeprl"},{"id":"2603.02155","title":"Near-Optimal Regret for KL-Regularized Multi-Armed Bandits","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2305.08359","title":"Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2311.07876","title":"Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2503.12020","title":"Variance-Dependent Regret Lower Bounds for Contextual Bandits","created":"2025-03-15","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":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2311.00973","title":"Federated Linear Bandits with Finite Adversarial Actions","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2411.05979","title":"Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2502.02486","title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2403.10732","title":"Variance-Dependent Regret Bounds for Non-stationary Linear Bandits","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2511.02123","title":"Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2402.08998","title":"Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2410.14992","title":"Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2508.02103","title":"Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation","created":"2025-08-04","cited_by_count":1,"area":"deeprl"},{"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":"2609.00193","title":"Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost","created":"2026-08-31","cited_by_count":1,"area":"deeprl"},{"id":"2407.13622","title":"Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2504.09339","title":"Towards Optimal Differentially Private Regret Bounds in Linear MDPs","created":"2025-04-12","cited_by_count":0,"area":"deeprl"},{"id":"2505.12037","title":"Adaptive Resolving Methods for Markov Decision Processes with Function Approximations","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2507.12584","title":"Second-Order Bounds for [0,1]-Valued Regression via Betting Loss","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2601.23164","title":"Stochastic Linear Bandits with Parameter Noise","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2605.07218","title":"Improved Model-based Reinforcement Learning with Smooth Kernels","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.23679","title":"Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.33246","title":"Minimax-Optimality of Posterior Sampling for Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}