{"total":7,"rows":[{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"id":"2202.02881","title":"Approximate Policy Iteration with Bisimulation Metrics","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2107.11053","title":"An Adaptive State Aggregation Algorithm for Markov Decision Processes","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2212.08949","title":"Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off","created":"2022-12-17","cited_by_count":1,"area":null}],"next_cursor":null}