{"total":11,"rows":[{"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":"2310.08833","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes","created":"2023-10-13","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":"2405.17108","title":"Finding good policies in average-reward Markov Decision Processes without prior knowledge","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"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":"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":"2509.14203","title":"Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2606.16729","title":"Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process","created":"2026-06-15","cited_by_count":3,"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":"2410.14992","title":"Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span","created":"2024-10-19","cited_by_count":1,"area":null}],"next_cursor":null}