{"id":"https://openalex.org/W4415203462","doi":"https://doi.org/10.1007/s42484-026-00359-8","title":"Hybrid reward-driven reinforcement learning for efficient quantum circuit synthesis","display_name":"Hybrid reward-driven reinforcement learning for efficient quantum circuit synthesis","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W4415203462","doi":"https://doi.org/10.1007/s42484-026-00359-8"},"language":"en","primary_location":{"id":"doi:10.1007/s42484-026-00359-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00359-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00359-8.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00359-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112007938","display_name":"Sara Giordano","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sara Giordano","raw_affiliation_strings":["Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023046061","display_name":"Kornikar Sen","orcid":"https://orcid.org/0000-0002-7007-0843"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kornikar Sen","raw_affiliation_strings":["Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058525159","display_name":"M. A. Mart\u00edn-Delgado","orcid":"https://orcid.org/0000-0003-2746-5062"},"institutions":[{"id":"https://openalex.org/I118091203","display_name":"Universidad San Pablo CEU","ror":"https://ror.org/00tvate34","country_code":"ES","type":"education","lineage":["https://openalex.org/I118091203","https://openalex.org/I2801318690"]},{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miguel A. Martin-Delgado","raw_affiliation_strings":["CCS-Center for Computational Simulation, Campus de Montegancedo Universidad Politecnica de Madrid (UPM), Av. de Montepr\u00edncipe, Boadilla del Monte, 28660, Madrid, Spain","Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CCS-Center for Computational Simulation, Campus de Montegancedo Universidad Politecnica de Madrid (UPM), Av. de Montepr\u00edncipe, Boadilla del Monte, 28660, Madrid, Spain","institution_ids":["https://openalex.org/I88060688","https://openalex.org/I118091203"]},{"raw_affiliation_string":"Departamento de F\u00edsica Te\u00f3rica, Universidad Complutense de Madrid, Plaza de las Ciencias 1. Ciudad Universitaria, Madrid, 28040, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112007938"],"corresponding_institution_ids":["https://openalex.org/I121748325"],"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":0.00789878,"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":0.9965999722480774,"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":0.9965999722480774,"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":0.9889000058174133,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9782000184059143,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6186000108718872},{"id":"https://openalex.org/keywords/quantum-circuit","display_name":"Quantum circuit","score":0.5990999937057495},{"id":"https://openalex.org/keywords/quantum-gate","display_name":"Quantum gate","score":0.5958999991416931},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.538100004196167},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4505999982357025},{"id":"https://openalex.org/keywords/electronic-circuit","display_name":"Electronic circuit","score":0.4474000036716461},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6241999864578247},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C124148022","wikidata":"https://www.wikidata.org/wiki/Q2122210","display_name":"Quantum circuit","level":5,"score":0.5990999937057495},{"id":"https://openalex.org/C58849907","wikidata":"https://www.wikidata.org/wiki/Q2118982","display_name":"Quantum gate","level":4,"score":0.5958999991416931},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4805999994277954},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C15706264","wikidata":"https://www.wikidata.org/wiki/Q230883","display_name":"Quantum state","level":3,"score":0.4099999964237213},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C137019171","wikidata":"https://www.wikidata.org/wiki/Q2623817","display_name":"Quantum algorithm","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C2778926657","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum system","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C186468114","wikidata":"https://www.wikidata.org/wiki/Q836478","display_name":"Quantum network","level":4,"score":0.26170000433921814},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s42484-026-00359-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00359-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00359-8.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.16641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16641","pdf_url":"https://arxiv.org/pdf/2507.16641","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":"pmh:doi:10.48550/arxiv.2507.16641","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2507.16641","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.16641","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s42484-026-00359-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-026-00359-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-026-00359-8.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1325701057","display_name":null,"funder_award_id":"PRTR-C17.I1","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G2166634996","display_name":null,"funder_award_id":"PRTR-C17.I1","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3424441068","display_name":null,"funder_award_id":"W911NF-14-1","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5166746559","display_name":null,"funder_award_id":"W911NF-14-1-0103","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G531036588","display_name":null,"funder_award_id":"C17.I1","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G686748096","display_name":null,"funder_award_id":"PRTR-C17","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415203462.pdf","grobid_xml":"https://content.openalex.org/works/W4415203462.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2895285911","https://openalex.org/W2150528339","https://openalex.org/W2902929788","https://openalex.org/W2996387336","https://openalex.org/W2761015455","https://openalex.org/W2074394986","https://openalex.org/W4309065661","https://openalex.org/W4395051522","https://openalex.org/W1971384536","https://openalex.org/W4391598136","https://openalex.org/W2961408814","https://openalex.org/W7124172776","https://openalex.org/W3121342653","https://openalex.org/W2792315573","https://openalex.org/W1974928788","https://openalex.org/W2795921402","https://openalex.org/W2006575921","https://openalex.org/W4307244186","https://openalex.org/W2152747729","https://openalex.org/W2794633558","https://openalex.org/W4210735526","https://openalex.org/W1986556555","https://openalex.org/W84874842","https://openalex.org/W2739908270","https://openalex.org/W580957117","https://openalex.org/W4389160991","https://openalex.org/W2624637765","https://openalex.org/W4385065411","https://openalex.org/W2032146159","https://openalex.org/W2145339207","https://openalex.org/W4388962824","https://openalex.org/W2995202285","https://openalex.org/W1616620037","https://openalex.org/W1967883933","https://openalex.org/W2941137921","https://openalex.org/W2103368228","https://openalex.org/W4406261702","https://openalex.org/W2102660061","https://openalex.org/W1503834475","https://openalex.org/W4384917131","https://openalex.org/W4410616566","https://openalex.org/W1491843047","https://openalex.org/W1980035368","https://openalex.org/W32403112","https://openalex.org/W4307492550","https://openalex.org/W2101786389","https://openalex.org/W4411275241"],"related_works":[],"abstract_inverted_index":{"A":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"framework":[4,68,170],"is":[5,105],"introduced":[6],"for":[7,149,215],"the":[8,31,60,64,81,84,112,132,157,169,182,201],"efficient":[9],"synthesis":[10],"of":[11,63,115,137],"quantum":[12,18,40,54,203,209,216],"circuits":[13,162],"that":[14,79,91,156,190],"generate":[15],"specified":[16],"target":[17,85],"states":[19],"from":[20],"a":[21,26,52,70,75,106,172,212],"fixed":[22],"initial":[23],"state,":[24],"addressing":[25],"central":[27],"challenge":[28],"in":[29,109],"both":[30],"Noisy":[32],"Intermediate-Scale":[33],"Quantum":[34],"(NISQ)":[35],"era":[36],"and":[37,100,129,185,206],"future":[38],"fault-tolerant":[39],"computing.":[41],"The":[42,67,187],"approach":[43],"utilizes":[44],"tabular":[45],"Q-learning,":[46],"based":[47],"on":[48,117,145],"action":[49],"sequences,":[50],"within":[51],"discretized":[53],"state":[55,86,102,204],"space,":[56],"to":[57,111,151,171],"effectively":[58],"manage":[59],"exponential":[61],"growth":[62],"space":[65,205],"dimension.":[66],"introduces":[69],"hybrid":[71],"reward":[72,78],"mechanism,":[73],"combining":[74],"static,":[76],"domain-informed":[77],"guides":[80],"agent":[82],"toward":[83],"with":[87,163,194],"customizable":[88],"dynamic":[89],"penalties":[90],"discourage":[92],"inefficient":[93],"circuit":[94,217],"structures":[95],"such":[96],"as":[97],"gate":[98,165,174],"congestion":[99],"redundant":[101],"revisits.":[103],"This":[104],"circuit-aware":[107,197],"reward,":[108],"contrast":[110],"current":[113],"trend":[114],"works":[116],"this":[118,191],"topic,":[119],"which":[120],"are":[121],"primarily":[122],"fidelity-based.":[123],"By":[124],"leveraging":[125],"sparse":[126],"matrix":[127],"representations":[128],"state-space":[130],"discretization,":[131],"method":[133],"enables":[134],"practical":[135],"navigation":[136],"high-dimensional":[138],"environments":[139],"while":[140],"minimizing":[141],"computational":[142],"overhead.":[143],"Benchmarking":[144],"graph-state":[146],"preparation":[147],"tasks":[148],"up":[150],"seven":[152],"qubits,":[153],"we":[154],"demonstrate":[155],"algorithm":[158],"consistently":[159],"discovers":[160],"minimal-depth":[161],"optimized":[164],"counts.":[166],"Moreover,":[167],"extending":[168],"universal":[173],"set":[175],"still":[176],"yields":[177],"low":[178],"depth":[179],"circuits,":[180,210],"highlighting":[181],"algorithm\u2019s":[183],"robustness":[184],"adaptability.":[186],"results":[188],"confirm":[189],"RL-driven":[192],"approach,":[193],"our":[195],"completely":[196],"method,":[198],"efficiently":[199],"explores":[200],"complex":[202],"synthesizes":[207],"near-optimal":[208],"providing":[211],"resource-efficient":[213],"foundation":[214],"optimization.":[218]},"counts_by_year":[],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-16T00:00:00"}