{"total":10,"rows":[{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2210.05918","title":"Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation","created":"2022-10-12","cited_by_count":23,"area":null},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","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":"2302.01450","title":"Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2203.11489","title":"A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle","created":"2022-03-22","cited_by_count":4,"area":null},{"id":"2309.16819","title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2312.04905","title":"Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null}],"next_cursor":null}