{"total":12,"rows":[{"id":"2103.03104","title":"Learning to run a Power Network Challenge: a Retrospective Analysis","created":"2021-03-02","cited_by_count":55,"area":null},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2112.06061","title":"OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion","created":"2021-12-11","cited_by_count":10,"area":null},{"id":"2207.10330","title":"Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design","created":"2022-07-21","cited_by_count":8,"area":null},{"id":"2103.11775","title":"Measuring and modeling the motor system with machine learning","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2407.11658","title":"Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2110.02129","title":"A study of first-passage time minimization via Q-learning in heated gridworlds","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2205.08369","title":"Applications of Reinforcement Learning in Deregulated Power Market: A Comprehensive Review","created":"2022-05-07","cited_by_count":0,"area":null}],"next_cursor":null}