{"total":11,"rows":[{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2105.00704","title":"Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2021-05-03","cited_by_count":7,"area":null},{"id":"2111.02787","title":"Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets","created":"2021-11-03","cited_by_count":3,"area":null},{"id":"2102.04220","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2110.13523","title":"Automating Control of Overestimation Bias for Reinforcement Learning","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2203.10445","title":"Smoothing Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2102.11717","title":"Greedy-Step Off-Policy Reinforcement Learning","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2307.04210","title":"Investigating the Edge of Stability Phenomenon in Reinforcement Learning","created":"2023-07-09","cited_by_count":0,"area":null},{"id":"2609.35897","title":"Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}