{"total":109,"rows":[{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96,"area":null},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92,"area":null},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87,"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":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83,"area":null},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"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":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","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":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"area":null},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"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":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2303.02783","title":"Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning","created":"2023-03-05","cited_by_count":44,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"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":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37,"area":null},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36,"area":null},{"id":"2106.07046","title":"Towards Tight Bounds on the Sample Complexity of Average-reward MDPs","created":"2021-06-13","cited_by_count":33,"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":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2212.00603","title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP","created":"2022-12-01","cited_by_count":29,"area":null},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29,"area":null},{"id":"2306.16394","title":"Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes","created":"2023-06-28","cited_by_count":29,"area":null},{"id":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2112.08451","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","created":"2021-12-15","cited_by_count":24,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2106.14352","title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning","created":"2021-06-28","cited_by_count":22,"area":null},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2110.08440","title":"Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"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":"2112.13109","title":"Accelerated and instance-optimal policy evaluation with linear function approximation","created":"2021-12-24","cited_by_count":18,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","cited_by_count":18,"area":null},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","cited_by_count":17,"area":null},{"id":"2403.11477","title":"Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs","created":"2024-03-18","cited_by_count":17,"area":null},{"id":"2112.05244","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","created":"2021-12-09","cited_by_count":16,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2208.10458","title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15,"area":"offlinerl"},{"id":"2310.08833","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","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":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14,"area":null},{"id":"2205.14211","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal","created":"2022-05-27","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":"2206.04044","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","created":"2022-06-08","cited_by_count":11,"area":null},{"id":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2309.17262","title":"Estimation and Inference in Distributional Reinforcement Learning","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2404.11509","title":"VC Theory for Inventory Policies","created":"2024-04-17","cited_by_count":8,"area":"deeprl"},{"id":"2405.12952","title":"Truncated Variance Reduced Value Iteration","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2301.10932","title":"On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures","created":"2023-01-26","cited_by_count":7,"area":null},{"id":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2402.07598","title":"Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model","created":"2024-02-12","cited_by_count":7,"area":"deeprl"},{"id":"2411.07591","title":"Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization","created":"2024-11-12","cited_by_count":6,"area":"deeprl"},{"id":"2311.13469","title":"Span-Based Optimal Sample Complexity for Average Reward MDPs","created":"2023-11-22","cited_by_count":5,"area":null},{"id":"2502.11238","title":"Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2506.00286","title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model","created":"2025-05-30","cited_by_count":5,"area":"deeprl"},{"id":"2510.20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","created":"2025-10-23","cited_by_count":5,"area":"deeprl"},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","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":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2502.09417","title":"A Survey of Reinforcement Learning for Optimization in Automation","created":"2025-02-13","cited_by_count":4,"area":"deeprl"},{"id":"2509.16586","title":"Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2103.00299","title":"Primal-Dual Stochastic Mirror Descent for MDPs","created":"2021-02-27","cited_by_count":3,"area":null},{"id":"2510.18687","title":"Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2105.08748","title":"Learning to Act Safely with Limited Exposure and Almost Sure Certainty","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2501.02652","title":"A View of the Certainty-Equivalence Method for PAC RL as an Application of the Trajectory Tree Method","created":"2025-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2503.06751","title":"Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints","created":"2025-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2505.13213","title":"Diffusion Models with Double Guidance: Generate with aggregated datasets","created":"2025-05-19","cited_by_count":2,"area":"diffusion"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","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":"2410.02994","title":"Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","created":"2024-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","cited_by_count":1,"area":"deeprl"},{"id":"2604.07323","title":"Gaussian Approximation for Asynchronous Q-learning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.16111","title":"Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.21763","title":"On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2605.31309","title":"Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2209.08682","title":"Towards Robust Off-Policy Evaluation via Human Inputs","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2303.09716","title":"A New Policy Iteration Algorithm For Reinforcement Learning in Zero-Sum Markov Games","created":"2023-03-17","cited_by_count":0,"area":null},{"id":"2402.11877","title":"Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2403.11544","title":"RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2405.04026","title":"Federated Control in Markov Decision Processes","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2408.06544","title":"Variance-Reduced Cascade Q-learning: Algorithms and Sample Complexity","created":"2024-08-13","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"}],"next_cursor":"100"}