{"total":12,"rows":[{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2303.11166","title":"Imitating Graph-Based Planning with Goal-Conditioned Policies","created":"2023-03-20","cited_by_count":13,"area":null},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7,"area":null},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2210.11237","title":"Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2107.06405","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2203.11677","title":"Robust Action Gap Increasing with Clipped Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2109.09037","title":"Dual Behavior Regularized Reinforcement Learning","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2205.09967","title":"A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning","created":"2022-05-20","cited_by_count":0,"area":null},{"id":"2206.08499","title":"A Parametric Class of Approximate Gradient Updates for Policy Optimization","created":"2022-06-17","cited_by_count":0,"area":null}],"next_cursor":null}