{"total":10,"rows":[{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2210.16956","title":"Reward Shaping Using Convolutional Neural Network","created":"2022-10-30","cited_by_count":3,"area":null},{"id":"2205.13718","title":"Off-Beat Multi-Agent Reinforcement Learning","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2306.12640","title":"On Addressing the Limitations of Graph Neural Networks","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2202.09489","title":"Shaping Advice in Deep Reinforcement Learning","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2203.13424","title":"Dealing with Sparse Rewards Using Graph Neural Networks","created":"2022-03-25","cited_by_count":0,"area":null}],"next_cursor":null}