{"total":65,"rows":[{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"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":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"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":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","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":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"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":"2103.01422","title":"Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learning","created":"2021-03-02","cited_by_count":15,"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":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","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":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"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":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","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":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2201.10542","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","created":"2022-01-25","cited_by_count":5,"area":null},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2101.03641","title":"Learning Augmented Index Policy for Optimal Service Placement at the Network Edge","created":"2021-01-10","cited_by_count":4,"area":null},{"id":"2109.03396","title":"A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2510.20725","title":"No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes","created":"2025-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2207.09090","title":"Actor-Critic based Improper Reinforcement Learning","created":"2022-07-19","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":"2306.02574","title":"Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2405.19017","title":"Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling","created":"2024-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2410.19705","title":"Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2412.11743","title":"Generalized Bayesian deep reinforcement learning","created":"2024-12-16","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":"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":"2209.03596","title":"An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2405.18793","title":"Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning","created":"2024-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2406.07992","title":"A Federated Online Restless Bandit Framework for Cooperative Resource Allocation","created":"2024-06-12","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":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","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":"2603.20604","title":"Bayesian Learning in Episodic Zero-Sum Games","created":"2026-03-21","cited_by_count":1,"area":"alignment"},{"id":"2102.08201","title":"Improper Reinforcement Learning with Gradient-based Policy Optimization","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2202.10008","title":"Double Thompson Sampling in Finite stochastic Games","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2308.02391","title":"Learning Optimal Admission Control in Partially Observable Queueing Networks","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2309.15737","title":"Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2310.10107","title":"Posterior Sampling-based Online Learning for Episodic POMDPs","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2401.06710","title":"Model-Free Approximate Bayesian Learning for Large-Scale Conversion Funnel Optimization","created":"2024-01-12","cited_by_count":0,"area":null},{"id":"2403.10638","title":"A resource-constrained stochastic scheduling algorithm for homeless street outreach and gleaning edible food","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2404.16920","title":"Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks","created":"2024-04-25","cited_by_count":0,"area":"deeprl"},{"id":"2405.08253","title":"Thompson Sampling for Infinite-Horizon Discounted Decision Processes","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2410.19919","title":"Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces","created":"2024-10-25","cited_by_count":0,"area":"deeprl"},{"id":"2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2606.04845","title":"Bayesian learning for the stochastic shortest path problem","created":"2026-06-03","cited_by_count":0,"area":null},{"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"}],"next_cursor":null}