{"total":99,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78,"area":"offlinerl"},{"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":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"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":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52,"area":null},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49,"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":"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":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"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":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44,"area":null},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"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":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38,"area":null},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"id":"2104.11186","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","created":"2021-04-22","cited_by_count":34,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27,"area":null},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2404.18909","title":"Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty","created":"2024-04-29","cited_by_count":25,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2106.08377","title":"Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path","created":"2021-06-15","cited_by_count":23,"area":null},{"id":"2102.06875","title":"Improved Corruption Robust Algorithms for Episodic Reinforcement Learning","created":"2021-02-13","cited_by_count":20,"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":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18,"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":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14,"area":"offlinerl"},{"id":"2112.09859","title":"Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP","created":"2021-12-18","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":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13,"area":"offlinerl"},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"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":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","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":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2102.07663","title":"Causal Markov Decision Processes: Learning Good Interventions Efficiently","created":"2021-02-15","cited_by_count":7,"area":null},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2302.01477","title":"A Reduction-based Framework for Sequential Decision Making with Delayed Feedback","created":"2023-02-03","cited_by_count":7,"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":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2205.13044","title":"Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments","created":"2022-05-25","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":"2403.11637","title":"The Value of Reward Lookahead in Reinforcement Learning","created":"2024-03-18","cited_by_count":6,"area":"deeprl"},{"id":"2410.22908","title":"Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2208.08056","title":"Sampling Through the Lens of Sequential Decision Making","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2210.04946","title":"Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path","created":"2022-10-10","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":"2305.08359","title":"Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs","created":"2023-05-15","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":"2408.10381","title":"Efficient Reinforcement Learning in Probabilistic Reward Machines","created":"2024-08-19","cited_by_count":4,"area":"deeprl"},{"id":"2410.24071","title":"Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs","created":"2024-10-31","cited_by_count":4,"area":"deeprl"},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2211.01743","title":"Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits","created":"2022-11-01","cited_by_count":3,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2505.14821","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","created":"2025-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2312.17248","title":"Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity","created":"2023-12-28","cited_by_count":2,"area":"lr"},{"id":"2403.01636","title":"Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks","created":"2024-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2603.23926","title":"Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs","created":"2026-03-25","cited_by_count":2,"area":"deeprl"},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2210.09255","title":"A Unified Algorithm for Stochastic Path Problems","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2510.06647","title":"Q-Learning with Fine-Grained Gap-Dependent Regret","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2602.15076","title":"Near-Optimal Sample Complexity for Online Constrained MDPs","created":"2026-02-16","cited_by_count":1,"area":"deeprl"},{"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":"2102.10025","title":"Learning to Stop with Surprisingly Few Samples","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"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":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.13188","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2601.10418","title":"Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching","created":"2026-01-15","cited_by_count":0,"area":"deeprl"},{"id":"2602.01453","title":"The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.03480","title":"Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","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":"2609.36486","title":"Optimal Multi-Reward Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}