{"id":"https://openalex.org/W4417183134","doi":"https://doi.org/10.1007/s42484-026-00383-8","title":"Quantum reinforcement learning in dynamic environments","display_name":"Quantum reinforcement learning in dynamic environments","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W4417183134","doi":"https://doi.org/10.1007/s42484-026-00383-8"},"language":"en","primary_location":{"id":"doi:10.1007/s42484-026-00383-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00383-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00383-8.pdf","source":{"id":"https://openalex.org/S4210217596","display_name":"Quantum Machine Intelligence","issn_l":"2524-4906","issn":["2524-4906","2524-4914"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00383-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117166407","display_name":"Oliver Sefrin","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Oliver Sefrin","raw_affiliation_strings":["Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, 89081, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, 89081, Ulm, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034289229","display_name":"Manuel Radons","orcid":"https://orcid.org/0000-0003-4272-2493"},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Radons","raw_affiliation_strings":["Bundesdruckerei GmbH, Kommandantenstra\u00dfe 18, 10969, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH, Kommandantenstra\u00dfe 18, 10969, Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047663050","display_name":"Lars Simon","orcid":"https://orcid.org/0000-0002-4896-6096"},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Simon","raw_affiliation_strings":["Bundesdruckerei GmbH, Kommandantenstra\u00dfe 18, 10969, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH, Kommandantenstra\u00dfe 18, 10969, Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082982745","display_name":"Sabine W\u00f6lk","orcid":"https://orcid.org/0000-0001-9137-4814"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210113675","display_name":"Center for Integrated Quantum Science and Technology","ror":"https://ror.org/01z25am55","country_code":"DE","type":"facility","lineage":["https://openalex.org/I100066346","https://openalex.org/I149899117","https://openalex.org/I196349391","https://openalex.org/I4210088365","https://openalex.org/I4210113675"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sabine W\u00f6lk","raw_affiliation_strings":["Center for Integrated Quantum Science and Technology (IQST), Ulm University, 89081, Ulm, Germany","Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, 89081, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Integrated Quantum Science and Technology (IQST), Ulm University, 89081, Ulm, Germany","institution_ids":["https://openalex.org/I4210113675"]},{"raw_affiliation_string":"Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, 89081, Ulm, Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5117166407"],"corresponding_institution_ids":["https://openalex.org/I2898391981"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01420839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9126999974250793,"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":0.9126999974250793,"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":0.03720000013709068,"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/T10622","display_name":"Quantum Mechanics and Applications","score":0.009399999864399433,"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":0.9110000133514404},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5328999757766724},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5259000062942505},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.476500004529953},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.45899999141693115},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43970000743865967},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4262000024318695},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.36730000376701355},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9110000133514404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5328999757766724},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5259000062942505},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3264999985694885},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C135402231","wikidata":"https://www.wikidata.org/wiki/Q898440","display_name":"Dissipation","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2630999982357025}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s42484-026-00383-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00383-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00383-8.pdf","source":{"id":"https://openalex.org/S4210217596","display_name":"Quantum Machine Intelligence","issn_l":"2524-4906","issn":["2524-4906","2524-4914"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.01691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01691","pdf_url":"https://arxiv.org/pdf/2507.01691","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s42484-026-00383-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00383-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00383-8.pdf","source":{"id":"https://openalex.org/S4210217596","display_name":"Quantum Machine Intelligence","issn_l":"2524-4906","issn":["2524-4906","2524-4914"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417183134.pdf","grobid_xml":"https://content.openalex.org/works/W4417183134.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Combining":[1],"quantum":[2],"computing":[3],"techniques":[4],"in":[5,31,115,138],"the":[6,18,62,71,74,92,102,128,139],"form":[7],"of":[8,61,73],"amplitude":[9],"amplification":[10],"with":[11,101,110,119],"classical":[12,112,152],"reinforcement":[13,24],"learning":[14,36,49,53,104],"has":[15,43],"led":[16],"to":[17,47,77,83,136,143,150],"so-called":[19],"\u201chybrid":[20],"agent":[21,42,76,94,114,131],"for":[22,34],"quantum-accessible":[23],"learning\u201d,":[25],"which":[26],"achieves":[27],"a":[28,97,111,120,144],"quadratic":[29],"speedup":[30],"sample":[32],"complexity":[33],"certain":[35],"problems.":[37],"So":[38],"far,":[39],"this":[40,67,88],"hybrid":[41,75,93,130],"only":[44],"been":[45],"applied":[46],"stationary":[48],"problems,":[50],"that":[51,127],"is,":[52],"problems":[54],"without":[55],"any":[56],"time":[57],"dependency":[58],"within":[59],"components":[60],"Markov":[63],"decision":[64],"process.":[65],"In":[66],"work,":[68],"we":[69,90],"investigate":[70],"applicability":[72],"dynamic":[78],"RL":[79,113,117],"environments":[80],"and":[81],"thus":[82],"more":[84],"realistic":[85],"scenarios.":[86],"To":[87],"end,":[89],"enhance":[91],"by":[95],"introducing":[96],"dissipation":[98],"mechanism":[99],"and,":[100],"resulting":[103],"agent,":[105],"perform":[106],"an":[107,116],"empirical":[108],"comparison":[109],"environment":[118,140],"time-dependent":[121],"reward":[122],"function.":[123],"Our":[124],"findings":[125],"suggest":[126],"modified":[129],"can":[132],"adapt":[133],"its":[134,151],"behavior":[135],"changes":[137],"quickly,":[141],"leading":[142],"higher":[145],"average":[146],"success":[147],"probability":[148],"compared":[149],"counterpart.":[153]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}