{"total":12,"rows":[{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"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":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2301.13757","title":"Toward Efficient Gradient-Based Value Estimation","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2309.07548","title":"Proximal Bellman mappings for reinforcement learning and their application to robust adaptive filtering","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2109.05110","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment","created":"2021-09-10","cited_by_count":3,"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":"2106.00922","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task","created":"2021-06-02","cited_by_count":2,"area":null}],"next_cursor":null}