{"total":9,"rows":[{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2302.12537","title":"Why Target Networks Stabilise Temporal Difference Methods","created":"2023-02-24","cited_by_count":13,"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":"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":"2306.09746","title":"Finite-Time Analysis of Temporal Difference Learning with Experience Replay","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2112.14417","title":"Control Theoretic Analysis of Temporal Difference Learning","created":"2021-12-29","cited_by_count":0,"area":null},{"id":"2201.09065","title":"Online Attentive Kernel-Based Temporal Difference Learning","created":"2022-01-22","cited_by_count":0,"area":null}],"next_cursor":null}