{"total":59,"rows":[{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"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":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"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":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"area":null},{"id":"2102.05284","title":"Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case","created":"2021-02-10","cited_by_count":28,"area":null},{"id":"2102.08940","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","created":"2021-02-17","cited_by_count":28,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2207.14211","title":"Regret Minimization and Convergence to Equilibria in General-sum Markov Games","created":"2022-07-28","cited_by_count":24,"area":null},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23,"area":null},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2209.13841","title":"Online Policy Optimization for Robust MDP","created":"2022-09-28","cited_by_count":19,"area":null},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17,"area":null},{"id":"2205.13451","title":"Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback","created":"2022-05-26","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":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15,"area":null},{"id":"2305.08629","title":"A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs","created":"2023-05-15","cited_by_count":15,"area":null},{"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":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","cited_by_count":14,"area":null},{"id":"2103.11559","title":"Provably Correct Optimization and Exploration with Non-linear Policies","created":"2021-03-22","cited_by_count":13,"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":"2202.03334","title":"Policy Optimization for Stochastic Shortest Path","created":"2022-02-07","cited_by_count":13,"area":null},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2310.11550","title":"Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","cited_by_count":10,"area":null},{"id":"2207.12463","title":"Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions","created":"2022-07-25","cited_by_count":9,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2306.07001","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","created":"2023-06-12","cited_by_count":7,"area":null},{"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":"2305.07911","title":"Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2306.09554","title":"Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","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":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2311.07876","title":"Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2502.05974","title":"Decision Making in Hybrid Environments: A Model Aggregation Approach","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"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":"2308.05471","title":"Provably Efficient Algorithm for Nonstationary Low-Rank MDPs","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2310.16473","title":"Policy Optimization via Adv2: Adversarial Learning on Advantage Functions","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2510.08882","title":"An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.17103","title":"Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2602.13700","title":"Optimal Regret for Policy Optimization in Contextual Bandits","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2602.13706","title":"Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2405.02188","title":"Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes","created":"2024-05-03","cited_by_count":1,"area":null},{"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}],"next_cursor":null}