{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:20:17Z","timestamp":1768310417671,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004725","name":"Ministry of Economic Affairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312001","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"4146-4153","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization"],"prefix":"10.1109","author":[{"given":"David","family":"Leeftink","sequence":"first","affiliation":[{"name":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"}]},{"given":"\u00c7a\u011fatay","family":"Y\u0131ld\u0131z","sequence":"additional","affiliation":[{"name":"University of Tübingen,Cluster of Excellence Machine Learning,Tübingen,Germany,72076"}]},{"given":"Steffen","family":"Ridderbusch","sequence":"additional","affiliation":[{"name":"University of Oxford,Control Group,Department of Engineering,Oxford,UK,OX1 3PJ"}]},{"given":"Max","family":"Hinne","sequence":"additional","affiliation":[{"name":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"}]},{"given":"Marcel","family":"Van Gerven","sequence":"additional","affiliation":[{"name":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203749319"},{"key":"ref3","volume-title":"Optimal Control Theory: An Introduction.","author":"Kirk","year":"2004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/0328054"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5220\/0001143902220229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-8176-4757-5","volume-title":"H-infinity Optimal Control and Related Minimax Design Problems: A Dynamic Game Approach.","author":"Ba\u015far","year":"2008"},{"key":"ref8","first-page":"7979","article-title":"Pontryagin differentiable programming: An end-to-end learning and control framework","volume":"33","author":"Jin","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"A Pontryagin perspective on reinforcement learning","volume-title":"Proceedings of the Sixth Annual Learning for Dynamics & Control Conference","author":"Eberhard"},{"key":"ref10","first-page":"2093","article-title":"Necessary optimality conditions for average cost minimization problems","author":"Bettiol","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2023011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/2200000049"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00498-021-00294-y"},{"key":"ref14","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on machine learning","author":"Deisenroth"},{"key":"ref15","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Kamthe"},{"key":"ref16","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"12009","article-title":"Continuous-time model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Yildiz"},{"key":"ref18","first-page":"42119","article-title":"Efficient exploration in continuous-time model-based reinforcement learning","volume":"36","author":"Treven","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0370-2693(87)91197-X"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.1979.4310229"},{"key":"ref21","volume-title":"Numerical Optimal Control (Draft)","author":"Gros","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/14786442608564127"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054411"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/a:1010091220143"},{"key":"ref26","first-page":"1049","article-title":"Sample-efficient cross-entropy method for real-time planning","volume-title":"Proceedings of the 2020 Conference on Robot Learning","volume":"155","author":"Pinneri"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/16M1062569"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0022-460X(79)90520-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(66)90009-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0771-050X(80)90013-3"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312001.pdf?arnumber=11312001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:13:43Z","timestamp":1768292023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312001","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}