{"id":"https://openalex.org/W4409377317","doi":"https://doi.org/10.1007/s42484-025-00269-1","title":"A hybrid learning agent for episodic learning tasks with unknown target distance","display_name":"A hybrid learning agent for episodic learning tasks with unknown target distance","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409377317","doi":"https://doi.org/10.1007/s42484-025-00269-1"},"language":"en","primary_location":{"id":"doi:10.1007/s42484-025-00269-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-025-00269-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-025-00269-1.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42484-025-00269-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045500991","display_name":"Oliver Sefrin","orcid":"https://orcid.org/0000-0002-1111-7787"},"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, Ulm, 89081, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, Ulm, 89081, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"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/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"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":["Institute for Complex Quantum Systems, Ulm University, Albert-Einstein-Allee 11, Ulm, 89081, Germany","Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, Ulm, 89081, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Complex Quantum Systems, Ulm University, Albert-Einstein-Allee 11, Ulm, 89081, Germany","institution_ids":["https://openalex.org/I4210113675","https://openalex.org/I196349391"]},{"raw_affiliation_string":"Institute of Quantum Technologies, German Aerospace Center (DLR), Wilhelm-Runge-Stra\u00dfe 10, Ulm, 89081, Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045500991"],"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":0.02934306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"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/T10320","display_name":"Neural Networks and Applications","score":0.987500011920929,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.974399983882904,"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/computer-science","display_name":"Computer science","score":0.4657137393951416},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.46048009395599365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501665234565735},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4268406629562378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4657137393951416},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.46048009395599365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501665234565735},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4268406629562378}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s42484-025-00269-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-025-00269-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-025-00269-1.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:elib.dlr.de:213691","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42484-025-00269-1>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s42484-025-00269-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-025-00269-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-025-00269-1.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/W4409377317.pdf","grobid_xml":"https://content.openalex.org/works/W4409377317.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1974824584","https://openalex.org/W1994630055","https://openalex.org/W2002372750","https://openalex.org/W2020918964","https://openalex.org/W2033368244","https://openalex.org/W2079905842","https://openalex.org/W2117941808","https://openalex.org/W2121981260","https://openalex.org/W2145339207","https://openalex.org/W2293506269","https://openalex.org/W2521267242","https://openalex.org/W2559394418","https://openalex.org/W2580674237","https://openalex.org/W2751139392","https://openalex.org/W2761015455","https://openalex.org/W2766447205","https://openalex.org/W2781738013","https://openalex.org/W2786295636","https://openalex.org/W2794602324","https://openalex.org/W2990961515","https://openalex.org/W2995202285","https://openalex.org/W2999912861","https://openalex.org/W3045093737","https://openalex.org/W3093944484","https://openalex.org/W3098550391","https://openalex.org/W3100358183","https://openalex.org/W3100931082","https://openalex.org/W3100993774","https://openalex.org/W3101119258","https://openalex.org/W3102180547","https://openalex.org/W3103841689","https://openalex.org/W3111162498","https://openalex.org/W3133779704","https://openalex.org/W3134827716","https://openalex.org/W3141755656","https://openalex.org/W3158332310","https://openalex.org/W3186736920","https://openalex.org/W3192537824","https://openalex.org/W3198177070","https://openalex.org/W4285390635","https://openalex.org/W4353055437","https://openalex.org/W4382237451","https://openalex.org/W4384824031","https://openalex.org/W4390669798","https://openalex.org/W4392975025","https://openalex.org/W4399881330","https://openalex.org/W4400284372","https://openalex.org/W4401596667","https://openalex.org/W4406898398","https://openalex.org/W4408648757","https://openalex.org/W6604778402","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"\u201chybrid":[2],"agent":[3,116,136],"for":[4,75,148,190,200],"quantum-accessible":[5],"reinforcement":[6,110],"learning,\u201d":[7],"as":[8,194,196],"defined":[9,62],"in":[10,67,80,106,121,179],"(Hamann":[11],"and":[12,24,69,108,112,168],"W\u00f6lk":[13],"New":[14],"J":[15],"Phys":[16],"24:033044":[17],"2022),":[18],"provides":[19],"a":[20,61,134,138,177],"proven":[21],"quasi-quadratic":[22],"speedup":[23,178,199],"is":[25,64,125],"experimentally":[26],"tested.":[27],"However,":[28],"the":[29,48,51,73,76,86,95,114,146,151,159],"standard":[30],"version":[31],"can":[32,117],"only":[33],"be":[34],"applied":[35],"to":[36,59,98,144,183],"episodic":[37],"learning":[38,111,123,192,204],"tasks":[39],"with":[40,101,137,167],"fixed":[41],"episode":[42,58,140,153,171,186],"length.":[43,154],"In":[44,129],"many":[45],"real-world":[46],"applications,":[47],"information":[49],"about":[50,150],"necessary":[52,152],"number":[53],"of":[54,88],"steps":[55],"within":[56],"an":[57,102,119,197],"reach":[60,94],"target":[63,74,104],"not":[65],"available":[66],"advance":[68],"especially":[70],"before":[71],"reaching":[72],"first":[77],"time.":[78],"Furthermore,":[79],"such":[81,122],"scenarios,":[82],"classical":[83,107,165,191],"agents":[84,193],"have":[85],"advantage":[87,120],"observing":[89],"at":[90],"which":[91],"step":[92],"they":[93],"target.":[96],"How":[97],"best":[99],"deal":[100],"unknown":[103,126],"distance":[105],"quantum":[109],"whether":[113],"hybrid":[115,135,161,203],"provide":[118],"scenarios":[124,181],"so":[127],"far.":[128],"this":[130],"work,":[131],"we":[132,157],"introduce":[133],"stochastic":[139],"length":[141,187],"selection":[142,172,188],"strategy":[143,189],"alleviate":[145],"need":[147],"knowledge":[149],"Through":[155],"simulations,":[156],"test":[158],"adapted":[160],"agent\u2019s":[162],"performance":[163],"versus":[164],"counterparts":[166],"without":[169],"similar":[170],"strategies.":[173],"Our":[174],"simulations":[175],"demonstrate":[176],"certain":[180],"due":[182],"our":[184,201],"developed":[185],"well":[195],"additional":[198],"resulting":[202],"agent.":[205]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
