{"total":11,"rows":[{"id":"2102.01567","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","created":"2021-02-02","cited_by_count":57,"area":null},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2307.02632","title":"Stability of Q-Learning Through Design and Optimism","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2112.07859","title":"Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games","created":"2021-12-15","cited_by_count":4,"area":null},{"id":"2302.09875","title":"Backstepping Temporal Difference Learning","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2210.09409","title":"Sufficient Exploration for Convex Q-learning","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2204.09801","title":"Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2606.22639","title":"Statistical Inference for Misspecified Contextual Bandits","created":"2026-06-21","cited_by_count":0,"area":null}],"next_cursor":null}