{"id":"https://openalex.org/W7123361128","doi":"https://doi.org/10.1109/cdc57313.2025.11312001","title":"Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization","display_name":"Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123361128","doi":"https://doi.org/10.1109/cdc57313.2025.11312001"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005491709","display_name":"David Leeftink","orcid":"https://orcid.org/0000-0002-9542-3334"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"David Leeftink","raw_affiliation_strings":["Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"],"affiliations":[{"raw_affiliation_string":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028778712","display_name":"\u00c7a\u011fatay Y\u0131ld\u0131z","orcid":"https://orcid.org/0000-0002-7808-502X"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"\u00c7a\u011fatay Y\u0131ld\u0131z","raw_affiliation_strings":["University of Tübingen,Cluster of Excellence Machine Learning,Tübingen,Germany,72076"],"affiliations":[{"raw_affiliation_string":"University of Tübingen,Cluster of Excellence Machine Learning,Tübingen,Germany,72076","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018720827","display_name":"Steffen Ridderbusch","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steffen Ridderbusch","raw_affiliation_strings":["University of Oxford,Control Group,Department of Engineering,Oxford,UK,OX1 3PJ"],"affiliations":[{"raw_affiliation_string":"University of Oxford,Control Group,Department of Engineering,Oxford,UK,OX1 3PJ","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082961171","display_name":"Max Hinne","orcid":"https://orcid.org/0000-0002-9279-6725"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Max Hinne","raw_affiliation_strings":["Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"],"affiliations":[{"raw_affiliation_string":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076682427","display_name":"M. H. J. C. van Gerven","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcel Van Gerven","raw_affiliation_strings":["Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ"],"affiliations":[{"raw_affiliation_string":"Radboud University,Donders Institute for Brain, Cognition and Behaviour,Department of Machine Learning and Neural Computing,Nijmegen,the Netherlands,6525XZ","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005491709"],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71590314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4146","last_page":"4153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5896000266075134,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5896000266075134,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06689999997615814,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.03999999910593033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.758400022983551},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6769999861717224},{"id":"https://openalex.org/keywords/hamiltonian","display_name":"Hamiltonian (control theory)","score":0.5113999843597412},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5047000050544739},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4878999888896942},{"id":"https://openalex.org/keywords/hamiltonian-mechanics","display_name":"Hamiltonian mechanics","score":0.46299999952316284},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.37400001287460327},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6769999861717224},{"id":"https://openalex.org/C130787639","wikidata":"https://www.wikidata.org/wiki/Q5645293","display_name":"Hamiltonian (control theory)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5023999810218811},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4839000105857849},{"id":"https://openalex.org/C136864674","wikidata":"https://www.wikidata.org/wiki/Q477921","display_name":"Hamiltonian mechanics","level":3,"score":0.46299999952316284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4417000114917755},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C121770821","wikidata":"https://www.wikidata.org/wiki/Q2072471","display_name":"Hamiltonian system","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C31010330","wikidata":"https://www.wikidata.org/wiki/Q1914255","display_name":"Maximum principle","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C86941820","wikidata":"https://www.wikidata.org/wiki/Q6865391","display_name":"Minimisation (clinical trials)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C141803461","wikidata":"https://www.wikidata.org/wiki/Q3491629","display_name":"Pontryagin's minimum principle","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322835","display_name":"Ministry of Economic Affairs","ror":"https://ror.org/042ge0913"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Without":[0],"exact":[1],"knowledge":[2],"of":[3,10,28,36,50],"the":[4,29,34,55,65],"true":[5],"system":[6,66],"dynamics,":[7],"optimal":[8,37,128],"control":[9,38,129],"non-linear":[11],"continuous-time":[12],"systems":[13,144],"requires":[14],"careful":[15],"treatment":[16,49],"under":[17],"epistemic":[18,51],"uncertainty.":[19],"In":[20],"this":[21],"work,":[22],"we":[23],"translate":[24],"a":[25,47,61,69,136],"probabilistic":[26,41,84,108],"interpretation":[27],"Pontryagin":[30],"maximum":[31],"principle":[32],"to":[33,60,82,112],"challenge":[35],"with":[39,58,145],"learned":[40,146],"dynamics":[42,85],"models.":[43],"Our":[44],"framework":[45,140],"provides":[46],"principled":[48,137],"uncertainty":[52],"by":[53],"minimizing":[54],"mean":[56,76],"Hamiltonian":[57,77,109],"respect":[59],"posterior":[62],"distribution":[63],"over":[64],"dynamicsWe":[67],"propose":[68],"multiple":[70],"shooting":[71],"numerical":[72],"method":[73],"that":[74,106],"leverages":[75],"minimization":[78],"and":[79,99,119,130,138],"is":[80],"scalable":[81],"large-scale":[83],"models,":[86],"including":[87],"ensemble":[88],"neural":[89],"ordinary":[90],"differential":[91],"equations.":[92],"Comparisons":[93],"against":[94],"other":[95],"baselines":[96],"in":[97,116,123],"online":[98,124],"offline":[100,117],"model-based":[101],"reinforcement":[102,131],"learning":[103],"tasks":[104],"show":[105],"our":[107,133],"approach":[110,134],"leads":[111],"reduced":[113],"trial":[114],"costs":[115],"settings":[118],"achieves":[120],"competitive":[121],"performance":[122],"scenarios.":[125],"By":[126],"bridging":[127],"learning,":[132],"offers":[135],"practical":[139],"for":[141],"controlling":[142],"uncertain":[143],"dynamics.":[147]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}