{"id":"https://openalex.org/W4416874942","doi":"https://doi.org/10.1109/qce65121.2025.10459","title":"Learning Control with Simulated Variational Quantum Policies in a Surrogate Cart-Pole Environment","display_name":"Learning Control with Simulated Variational Quantum Policies in a Surrogate Cart-Pole Environment","publication_year":2025,"publication_date":"2025-08-30","ids":{"openalex":"https://openalex.org/W4416874942","doi":"https://doi.org/10.1109/qce65121.2025.10459"},"language":null,"primary_location":{"id":"doi:10.1109/qce65121.2025.10459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qce65121.2025.10459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Quantum Computing and Engineering (QCE)","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/A5101328614","display_name":"Yize Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yize Sun","raw_affiliation_strings":["Siemens AG & MCML & LMU,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG & MCML & LMU,Munich,Germany","institution_ids":["https://openalex.org/I1325886976","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120532040","display_name":"Mohamad Hagog","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohamad Hagog","raw_affiliation_strings":["LMU Munich,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich,Munich,Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770641","display_name":"M. Weber","orcid":"https://orcid.org/0000-0002-3639-2267"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Weber","raw_affiliation_strings":["Siemens AG,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003471349","display_name":"Daniel Hein","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Hein","raw_affiliation_strings":["Siemens AG,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":["Siemens AG,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066743613","display_name":"Yunpu Ma","orcid":"https://orcid.org/0000-0001-6112-8794"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yunpu Ma","raw_affiliation_strings":["LMU Munich,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich,Munich,Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074808403","display_name":"Volker Tresp","orcid":"https://orcid.org/0000-0001-9428-3686"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Tresp","raw_affiliation_strings":["LMU Munich,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich,Munich,Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17898291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9003999829292297,"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"}},"topics":[{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9003999829292297,"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/T10020","display_name":"Quantum Information and Cryptography","score":0.026499999687075615,"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/T11804","display_name":"Quantum many-body systems","score":0.02250000089406967,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6902999877929688},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.6010000109672546},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5435000061988831},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4104999899864197},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.40230000019073486},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38040000200271606},{"id":"https://openalex.org/keywords/quantum-system","display_name":"Quantum system","score":0.35120001435279846},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34860000014305115}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6902999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201000213623047},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C2778926657","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum system","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C2984281365","wikidata":"https://www.wikidata.org/wiki/Q906781","display_name":"Quantum control","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C137019171","wikidata":"https://www.wikidata.org/wiki/Q2623817","display_name":"Quantum algorithm","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C15706264","wikidata":"https://www.wikidata.org/wiki/Q230883","display_name":"Quantum state","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/qce65121.2025.10459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qce65121.2025.10459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Quantum Computing and Engineering (QCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2796293949","https://openalex.org/W3141755656","https://openalex.org/W3178225342","https://openalex.org/W4318983914"],"related_works":[],"abstract_inverted_index":{"We":[0],"explore":[1],"the":[2,34,39,78,85],"use":[3],"of":[4,66,90],"pure":[5],"quantum":[6,11,79,101],"policies,":[7],"implemented":[8],"via":[9],"variational":[10],"circuits":[12],"(VQCs),":[13],"for":[14],"offline":[15,57,110],"reinforcement":[16],"learning":[17],"(RL).":[18],"In":[19],"contrast":[20],"to":[21],"hybrid":[22],"models,":[23],"our":[24],"policy":[25,41,53,80],"architecture":[26],"contains":[27],"no":[28],"classical":[29,40,86],"neural":[30],"layers.":[31],"Built":[32],"on":[33,82],"MOOSE":[35],"framework,":[36],"we":[37],"replace":[38],"with":[42,84],"a":[43,62,67,113],"VQC":[44],"enhanced":[45],"by":[46],"trainable":[47],"input":[48],"and":[49,93],"output":[50],"weights.":[51],"The":[52],"is":[54],"trained":[55],"entirely":[56],"using":[58],"synthetic":[59],"rollouts":[60],"from":[61],"learned":[63],"surrogate":[64],"model":[65],"physical":[68],"cart-pole":[69],"system.":[70],"Evaluation":[71],"in":[72,88,108],"this":[73],"simulated":[74],"environment":[75],"shows":[76],"that":[77,99],"performs":[81],"par":[83],"baseline":[87],"terms":[89],"stability,":[91],"smoothness,":[92],"reward":[94],"accumulation.":[95],"These":[96],"results":[97],"demonstrate":[98],"purely":[100],"models":[102],"can":[103],"effectively":[104],"learn":[105],"control":[106],"strategies":[107],"model-based":[109],"RL,":[111],"offering":[112],"promising":[114],"step":[115],"toward":[116],"real-world":[117],"quantum-enhanced":[118],"decision-making.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-01T00:00:00"}