{"total":55,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"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":"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":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"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":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","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":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"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":"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":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38,"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":"2303.02738","title":"Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback","created":"2023-03-05","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":"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":"2404.18909","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":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"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":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"area":"offlinerl"},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","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":"2302.00036","title":"Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor","created":"2023-01-31","cited_by_count":13,"area":null},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11,"area":"offlinerl"},{"id":"2205.14842","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","created":"2022-05-30","cited_by_count":9,"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":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"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":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2107.00685","title":"Gap-Dependent Bounds for Two-Player Markov Games","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2310.11138","title":"Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2301.02389","title":"Provable Reset-free Reinforcement Learning by No-Regret Reduction","created":"2023-01-06","cited_by_count":3,"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":"2407.10207","title":"Learning to Steer Markovian Agents under Model Uncertainty","created":"2024-07-14","cited_by_count":2,"area":null},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2507.12383","title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","created":"2025-07-16","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":"2509.14077","title":"Online Bayesian Risk-Averse Reinforcement Learning","created":"2025-09-17","cited_by_count":1,"area":"deeprl"},{"id":"2510.03181","title":"Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning","created":"2025-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2301.05630","title":"Decentralized model-free reinforcement learning in stochastic games with average-reward objective","created":"2023-01-13","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":"2501.13394","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","created":"2025-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2508.13963","title":"Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem","created":"2025-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2511.03595","title":"Tensor-Efficient High-Dimensional Q-learning","created":"2025-11-05","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":"2605.24345","title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.19854","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","created":"2026-07-22","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}