{"total":66,"rows":[{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"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":"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":"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":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","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":"2309.01922","title":"Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes","created":"2023-09-05","cited_by_count":26,"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":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"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":"2102.07301","title":"Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2021-02-15","cited_by_count":18,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2102.12661","title":"Online Learning for Unknown Partially Observable MDPs","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","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":"2106.05335","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2402.13903","title":"Dealing with unbounded gradients in stochastic saddle-point optimization","created":"2024-02-21","cited_by_count":16,"area":null},{"id":"2406.01234","title":"Achieving Tractable Minimax Optimal Regret in Average Reward MDPs","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2405.17108","title":"Finding good policies in average-reward Markov Decision Processes without prior knowledge","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2202.03463","title":"On learning Whittle index policy for restless bandits with scalable regret","created":"2022-02-07","cited_by_count":10,"area":null},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9,"area":"deeprl"},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","cited_by_count":8,"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":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8,"area":"deeprl"},{"id":"2405.15050","title":"Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs","created":"2024-05-23","cited_by_count":7,"area":"deeprl"},{"id":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"area":null},{"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":"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":"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":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2310.11684","title":"Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2110.03424","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","created":"2021-10-07","cited_by_count":2,"area":null},{"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":"2208.14407","title":"An Analysis of Model-Based Reinforcement Learning From Abstracted Observations","created":"2022-08-30","cited_by_count":2,"area":null},{"id":"2302.10667","title":"Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.02527","title":"Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2506.20910","title":"Faster Fixed-Point Methods for Multichain MDPs","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2603.00945","title":"Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.23926","title":"Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs","created":"2026-03-25","cited_by_count":2,"area":"deeprl"},{"id":"2605.11586","title":"Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret","created":"2026-05-12","cited_by_count":2,"area":"deeprl"},{"id":"2106.08771","title":"Reinforcement Learning for Markovian Bandits: Is Posterior Sampling more Scalable than Optimism?","created":"2021-06-16","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":"2411.06069","title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2506.20307","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","created":"2025-06-25","cited_by_count":1,"area":"offlinerl"},{"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":"2510.06647","title":"Q-Learning with Fine-Grained Gap-Dependent Regret","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2308.02391","title":"Learning Optimal Admission Control in Partially Observable Queueing Networks","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2308.14919","title":"On Reward Structures of Markov Decision Processes","created":"2023-08-28","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":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2410.19919","title":"Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces","created":"2024-10-25","cited_by_count":0,"area":"deeprl"},{"id":"2602.00781","title":"Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding","created":"2026-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.07725","title":"Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.39093","title":"Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation","created":"2026-09-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}