{"total":10,"rows":[{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2204.12937","title":"Learning to Transfer Role Assignment Across Team Sizes","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2209.12483","title":"Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning","created":"2022-09-26","cited_by_count":0,"area":null},{"id":"2307.10491","title":"Markov Decision Processes with Time-Varying Geometric Discounting","created":"2023-07-19","cited_by_count":0,"area":null}],"next_cursor":null}