{"id":"https://openalex.org/W7213414919","doi":"https://doi.org/10.48550/arxiv.2609.16266","title":"Towards Surrogate Based Dequantization of Quantum Reinforcement Learning","display_name":"Towards Surrogate Based Dequantization of Quantum Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213414919","doi":"https://doi.org/10.48550/arxiv.2609.16266"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.16266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16266","pdf_url":"https://arxiv.org/pdf/2609.16266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.16266","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092513064","display_name":"Pablo Rodriguez-Grasa","orcid":"https://orcid.org/0009-0009-8622-2088","observed_orcids":["https://orcid.org/0009-0009-8622-2088"]},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]},{"id":"https://openalex.org/I4210113430","display_name":"Tecnalia","ror":"https://ror.org/02fv8hj62","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210113430"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rodriguez-Grasa, Pablo","raw_affiliation_strings":["Department of Physical Chemistry , University of the Basque Country UPV/EHU , Apartado 644 , 48080 Bilbao , Spain","TECNALIA , Basque Research and Technology Alliance (BRTA) , 48160 Derio , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physical Chemistry , University of the Basque Country UPV/EHU , Apartado 644 , 48080 Bilbao , Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"TECNALIA , Basque Research and Technology Alliance (BRTA) , 48160 Derio , Spain","institution_ids":["https://openalex.org/I4210113430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042661222","display_name":"Sofi\u00e8ne Jerbi","orcid":"https://orcid.org/0000-0001-8171-5742","observed_orcids":["https://orcid.org/0000-0001-8171-5742"]},"institutions":[{"id":"https://openalex.org/I2800795503","display_name":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie","ror":"https://ror.org/02aj13c28","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2800795503"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jerbi, Sofiene","raw_affiliation_strings":["Dahlem Center for Complex Quantum Systems , Freie Universit\u00e4t Berlin , 14195 Berlin , Germany","Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie , 14109 Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dahlem Center for Complex Quantum Systems , Freie Universit\u00e4t Berlin , 14195 Berlin , Germany","institution_ids":["https://openalex.org/I75951250"]},{"raw_affiliation_string":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie , 14109 Berlin , Germany","institution_ids":["https://openalex.org/I2800795503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121118573","display_name":"Mikel Sanz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanz, Mikel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082705766","display_name":"Ryan Sweke","orcid":"https://orcid.org/0000-0002-6202-8864","observed_orcids":["https://orcid.org/0000-0002-6202-8864","https://orcid.org/0009-0006-1308-951X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sweke, Ryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9990000128746033,"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":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0006000000284984708,"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":0.0,"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/dequantization","display_name":"dequantization","score":0.9169999957084656},{"id":"https://openalex.org/keywords/quantum-reinforcement-learning","display_name":"quantum reinforcement learning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/variational-quantum-circuits","display_name":"variational quantum circuits","score":0.8930000066757202},{"id":"https://openalex.org/keywords/finite-sample-guarantees","display_name":"finite-sample guarantees","score":0.7519999742507935},{"id":"https://openalex.org/keywords/experience-replay","display_name":"experience replay","score":0.6570000052452087},{"id":"https://openalex.org/keywords/quantum-advantage","display_name":"quantum advantage","score":0.6570000052452087},{"id":"https://openalex.org/keywords/data-encoding","display_name":"data encoding","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6200000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4862000048160553},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C137019171","wikidata":"https://www.wikidata.org/wiki/Q2623817","display_name":"Quantum algorithm","level":3,"score":0.43470001220703125},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40119999647140503},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C2778926657","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum system","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C2779094486","wikidata":"https://www.wikidata.org/wiki/Q18811578","display_name":"Quantum machine learning","level":4,"score":0.2935999929904938},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C124148022","wikidata":"https://www.wikidata.org/wiki/Q2122210","display_name":"Quantum circuit","level":5,"score":0.26589998602867126},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C58849907","wikidata":"https://www.wikidata.org/wiki/Q2118982","display_name":"Quantum gate","level":4,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.16266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16266","pdf_url":"https://arxiv.org/pdf/2609.16266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.16266","doi":"https://doi.org/10.48550/arxiv.2609.16266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.16266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.16266","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16266","pdf_url":"https://arxiv.org/pdf/2609.16266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213414919.pdf","grobid_xml":"https://content.openalex.org/works/W7213414919.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3212939316","https://openalex.org/W4384824031","https://openalex.org/W4221166795","https://openalex.org/W4385011780","https://openalex.org/W3051329393","https://openalex.org/W3134744093","https://openalex.org/W4406894513","https://openalex.org/W6986780955","https://openalex.org/W3093944484","https://openalex.org/W4226407443"],"abstract_inverted_index":{"In":[0,16],"recent":[1,98],"years,":[2],"the":[3,17,77,90,120,141,173,193,201,206,240],"utility":[4],"of":[5,19,65,79,83,88,92,123,143,176,189,196,218,242],"parameterized":[6,178,198],"quantum":[7,28,32,58,93,179,199,219],"circuits":[8],"as":[9,31,246],"function":[10],"approximators":[11],"has":[12,24],"been":[13],"widely":[14],"studied.":[15],"context":[18],"reinforcement":[20,115,124],"learning,":[21,104],"this":[22,73,110,155,222],"approach":[23],"led":[25],"to":[26,71,114,171],"variational":[27,94],"algorithms":[29,86],"such":[30],"Q-learning.":[33],"While":[34],"these":[35,182,232,236,251],"methods":[36],"show":[37],"promising":[38],"empirical":[39],"results,":[40,183],"and":[41,205],"can":[42,54],"provide":[43,55,158,186],"provable":[44,57],"advantages":[45],"for":[46,63,102,162],"artificial":[47],"problems,":[48],"it":[49],"remains":[50],"unclear":[51],"whether":[52],"they":[53],"a":[56,127,146,187,197,215,247],"advantage":[59],"over":[60],"classical":[61,85,163,168,203],"approaches":[62],"problems":[64],"practical":[66],"relevance.":[67],"A":[68],"natural":[69],"way":[70],"investigate":[72],"question":[74],"is":[75],"through":[76],"lens":[78],"dequantization:":[80],"The":[81],"construction":[82],"efficient":[84],"capable":[87],"matching":[89],"performance":[91],"methods.":[95],"Building":[96],"on":[97,192],"kernel-based":[99],"dequantization":[100,112,217,229,248],"results":[101,237],"supervised":[103],"we":[105,118,157,184],"take":[106],"steps":[107],"towards":[108],"extending":[109],"surrogate-based":[111],"program":[113],"learning.":[116],"Specifically,":[117],"study":[119],"simplified":[121,223],"setting":[122],"learning":[125],"with":[126,167],"uniform":[128],"generative":[129],"model":[130],"in":[131,221],"which":[132,139,210],"uniformly":[133],"random":[134],"state-action":[135],"samples":[136],"are":[137,234],"available,":[138],"models":[140],"regime":[142],"sampling":[144],"from":[145,226],"large":[147],"experience":[148],"replay":[149],"buffer":[150],"after":[151],"sufficient":[152,190,252],"exploration.":[153],"Within":[154],"setting,":[156],"finite":[159],"sample":[160],"guarantees":[161,230],"kernelized":[164,211,243],"Fitted":[165,212],"Q-Iteration,":[166],"kernels":[169],"designed":[170],"match":[172],"inductive":[174],"bias":[175],"particular":[177],"circuits.":[180],"Using":[181],"then":[185],"set":[188],"conditions,":[191],"data-encoding":[194],"strategy":[195],"circuit,":[200],"corresponding":[202],"kernel,":[204],"problem":[207],"structure,":[208],"under":[209],"Q-Iteration":[213],"provides":[214],"meaningful":[216],"Q-learning,":[220],"setting.":[224],"Apart":[225],"providing":[227],"rigorous":[228],"when":[231,250],"conditions":[233,253],"met,":[235],"also":[238],"motivate":[239],"use":[241],"fitted":[244],"Q-iteration":[245],"heuristic":[249],"cannot":[254],"be":[255],"verified.":[256]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-17T00:00:00"}