{"total":10,"rows":[{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"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":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2205.08464","title":"Robust Losses for Learning Value Functions","created":"2022-05-17","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":"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":"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},{"id":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2203.10172","title":"Importance Sampling Placement in Off-Policy Temporal-Difference Methods","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2209.04624","title":"Gradient Descent Temporal Difference-difference Learning","created":"2022-09-10","cited_by_count":1,"area":null}],"next_cursor":null}