{"total":10,"rows":[{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2109.10312","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","created":"2021-09-21","cited_by_count":13,"area":null},{"id":"2212.02603","title":"Learning to Optimize in Model Predictive Control","created":"2022-12-05","cited_by_count":11,"area":null},{"id":"2212.02587","title":"Learning Sampling Distributions for Model Predictive Control","created":"2022-12-05","cited_by_count":10,"area":null},{"id":"2104.02863","title":"The Value of Planning for Infinite-Horizon Model Predictive Control","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2310.04590","title":"Deep Model Predictive Optimization","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2210.01426","title":"Continuous Monte Carlo Graph Search","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2210.08131","title":"Model-Free Characterizations of the Hamilton-Jacobi-Bellman Equation and Convex Q-Learning in Continuous Time","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2410.04929","title":"Goal-Conditioned Terminal Value Estimation for Real-time and Multi-task Model Predictive Control","created":"2024-10-07","cited_by_count":0,"area":null}],"next_cursor":null}