{"total":12,"rows":[{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2109.15316","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"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":"2205.13743","title":"Personalized Algorithmic Recourse with Preference Elicitation","created":"2022-05-27","cited_by_count":9,"area":null},{"id":"2203.04120","title":"Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2408.10162","title":"Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2101.04167","title":"First-Order Problem Solving through Neural MCTS based Reinforcement Learning","created":"2021-01-11","cited_by_count":2,"area":null},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2201.02874","title":"Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture","created":"2022-01-08","cited_by_count":0,"area":null},{"id":"2410.08875","title":"Online design of dynamic networks","created":"2024-10-11","cited_by_count":0,"area":null}],"next_cursor":null}