{"total":16,"rows":[{"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":"2203.03186","title":"Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm","created":"2022-03-07","cited_by_count":6,"area":null},{"id":"2206.08776","title":"Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms","created":"2022-06-17","cited_by_count":6,"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":"2309.16563","title":"CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2105.02135","title":"UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms","created":"2021-05-05","cited_by_count":1,"area":null},{"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":"2303.09629","title":"Online Reinforcement Learning in Periodic MDP","created":"2023-03-16","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":"2510.13476","title":"Towards Blackwell Optimality: Bellman Optimality Is All You Can Get","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2207.12045","title":"Online Reinforcement Learning for Periodic MDP","created":"2022-07-25","cited_by_count":0,"area":null},{"id":"2407.15662","title":"How to Shrink Confidence Sets for Many Equivalent Discrete Distributions?","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}