{"total":5,"rows":[{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"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":"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":"2601.18840","title":"Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2604.06837","title":"Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem","created":"2026-04-08","cited_by_count":0,"area":null}],"next_cursor":null}