{"total":63,"rows":[{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67,"area":null},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53,"area":null},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2102.03192","title":"Provably Efficient Algorithms for Multi-Objective Competitive RL","created":"2021-02-05","cited_by_count":22,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2301.13446","title":"Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments","created":"2023-01-31","cited_by_count":19,"area":null},{"id":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2301.12601","title":"Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents","created":"2023-01-30","cited_by_count":15,"area":null},{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2310.00817","title":"Learning to Make Adherence-Aware Advice","created":"2023-10-01","cited_by_count":13,"area":null},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2211.03413","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","created":"2022-11-07","cited_by_count":11,"area":null},{"id":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2206.14057","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2306.02399","title":"Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures","created":"2023-06-04","cited_by_count":8,"area":null},{"id":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2111.07615","title":"Optimism and Delays in Episodic Reinforcement Learning","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2210.00832","title":"Square-root regret bounds for continuous-time episodic Markov decision processes","created":"2022-10-03","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"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":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.01243","title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations","created":"2023-06-02","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":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2312.08369","title":"The Effective Horizon Explains Deep RL Performance in Stochastic Environments","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2411.00707","title":"Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2202.07995","title":"Branching Reinforcement Learning","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2205.10729","title":"Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path","created":"2022-05-22","cited_by_count":2,"area":null},{"id":"2502.17370","title":"A Refined Analysis of UCBVI","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2602.16363","title":"Improved Bounds for Reward-Agnostic and Reward-Free Exploration","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2301.04268","title":"Adversarial Online Multi-Task Reinforcement Learning","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2309.15395","title":"Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2407.05704","title":"Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.03707","title":"Online Learning of Optimal Sequential Testing Policies","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2608.21995","title":"Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}