{"id":"https://openalex.org/W3046924627","doi":"https://doi.org/10.1007/s42484-021-00049-7","title":"Quantum-accessible reinforcement learning beyond strictly epochal environments","display_name":"Quantum-accessible reinforcement learning beyond strictly epochal environments","publication_year":2021,"publication_date":"2021-08-02","ids":{"openalex":"https://openalex.org/W3046924627","doi":"https://doi.org/10.1007/s42484-021-00049-7","mag":"3046924627","pmid":"https://pubmed.ncbi.nlm.nih.gov/34723097"},"language":"en","primary_location":{"id":"doi:10.1007/s42484-021-00049-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-021-00049-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-021-00049-7.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42484-021-00049-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018259456","display_name":"Arne Hamann","orcid":"https://orcid.org/0000-0002-9016-3641"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"A. Hamann","raw_affiliation_strings":["Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Technikerstra\u00dfe 21a, 6020 Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0002-9016-3641","affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Technikerstra\u00dfe 21a, 6020 Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069043772","display_name":"Vedran Dunjko","orcid":"https://orcid.org/0000-0002-2632-7955"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"V. Dunjko","raw_affiliation_strings":["LIACS, Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"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/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]},{"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":["AT","DE"],"is_corresponding":true,"raw_author_name":"S. W\u00f6lk","raw_affiliation_strings":["Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Technikerstra\u00dfe 21a, 6020 Innsbruck, Austria","Present Address: Institute of Quantum Technologies, German Aerospace Center (DLR), D-89077 Ulm, Germany","Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Innsbruck, Austria","Institute of Quantum Technologies, German Aerospace Center (DLR), Ulm, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9137-4814","affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Technikerstra\u00dfe 21a, 6020 Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]},{"raw_affiliation_string":"Present Address: Institute of Quantum Technologies, German Aerospace Center (DLR), D-89077 Ulm, Germany","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institut f\u00fcr Theoretische Physik, Universit\u00e4t Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]},{"raw_affiliation_string":"Institute of Quantum Technologies, German Aerospace Center (DLR), Ulm, Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082982745"],"corresponding_institution_ids":["https://openalex.org/I190249584","https://openalex.org/I2898391981"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2798,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61034798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"2","first_page":"22","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9103000164031982,"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":0.9103000164031982,"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":0.031099999323487282,"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"}},{"id":"https://openalex.org/T10020","display_name":"Quantum Information and Cryptography","score":0.02070000022649765,"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":0.8382859826087952},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7814739942550659},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.6796311140060425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6719807386398315},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5280799865722656},{"id":"https://openalex.org/keywords/quantum-machine-learning","display_name":"Quantum machine learning","score":0.4673355519771576},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.46723324060440063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4538666903972626},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.352692186832428},{"id":"https://openalex.org/keywords/quantum-algorithm","display_name":"Quantum algorithm","score":0.27746152877807617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21160352230072021},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07240322232246399},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.07193061709403992}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8382859826087952},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7814739942550659},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.6796311140060425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6719807386398315},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5280799865722656},{"id":"https://openalex.org/C2779094486","wikidata":"https://www.wikidata.org/wiki/Q18811578","display_name":"Quantum machine learning","level":4,"score":0.4673355519771576},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.46723324060440063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4538666903972626},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.352692186832428},{"id":"https://openalex.org/C137019171","wikidata":"https://www.wikidata.org/wiki/Q2623817","display_name":"Quantum algorithm","level":3,"score":0.27746152877807617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21160352230072021},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07240322232246399},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.07193061709403992},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s42484-021-00049-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-021-00049-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-021-00049-7.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":"pmid:34723097","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34723097","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantum machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2008.01481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.01481","pdf_url":"https://arxiv.org/pdf/2008.01481","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:europepmc.org:7442552","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8550166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8550166","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8550166","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Quantum Mach Intell","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2008.01481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.01481","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-journal"}],"best_oa_location":{"id":"doi:10.1007/s42484-021-00049-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42484-021-00049-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42484-021-00049-7.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":[{"id":"https://openalex.org/G249262831","display_name":null,"funder_award_id":"024.003.037","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046924627.pdf","grobid_xml":"https://content.openalex.org/works/W3046924627.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W61065943","https://openalex.org/W1492999010","https://openalex.org/W1965765304","https://openalex.org/W1994630055","https://openalex.org/W2002372750","https://openalex.org/W2020918964","https://openalex.org/W2031056773","https://openalex.org/W2079905842","https://openalex.org/W2115524942","https://openalex.org/W2122410182","https://openalex.org/W2126323053","https://openalex.org/W2126338609","https://openalex.org/W2132764286","https://openalex.org/W2151365767","https://openalex.org/W2521267242","https://openalex.org/W2559394418","https://openalex.org/W2624637765","https://openalex.org/W2751139392","https://openalex.org/W2769018026","https://openalex.org/W2773252567","https://openalex.org/W2788945937","https://openalex.org/W2792315573","https://openalex.org/W2798434869","https://openalex.org/W2799011018","https://openalex.org/W2896792097","https://openalex.org/W2939567823","https://openalex.org/W2948580656","https://openalex.org/W2964327027","https://openalex.org/W2969044738","https://openalex.org/W3034336799","https://openalex.org/W3041308142","https://openalex.org/W3133779704"],"related_works":["https://openalex.org/W547392","https://openalex.org/W3471107","https://openalex.org/W8539471","https://openalex.org/W13926559","https://openalex.org/W4651166","https://openalex.org/W8637261","https://openalex.org/W11104910","https://openalex.org/W5779190","https://openalex.org/W13660921","https://openalex.org/W8728285"],"abstract_inverted_index":{"In":[0,129,177],"recent":[1],"years,":[2],"quantum-enhanced":[3],"machine":[4],"learning":[5,25],"has":[6],"emerged":[7],"as":[8],"a":[9,43,56,94,153,201],"particularly":[10],"fruitful":[11],"application":[12],"of":[13,18,29,61,64,80,214,218],"quantum":[14,31,44,78,115],"algorithms,":[15],"covering":[16],"aspects":[17],"supervised,":[19],"unsupervised":[20],"and":[21,36,52,160],"reinforcement":[22,220],"learning.":[23,221],"Reinforcement":[24],"offers":[26],"numerous":[27],"options":[28],"how":[30],"theory":[32],"can":[33,73,84,106],"be":[34,74,86,107,171],"applied,":[35],"is":[37,140,145,188,207],"arguably":[38],"the":[39,65,91,138,195,204,215],"least":[40],"explored,":[41],"from":[42],"perspective.":[45],"Here,":[46],"an":[47,50,148,182],"agent":[48],"explores":[49],"environment":[51,139],"tries":[53],"to":[54,110,147,173],"find":[55],"behavior":[57],"optimizing":[58],"some":[59],"figure":[60],"merit.":[62],"Some":[63],"first":[66,216],"approaches":[67],"investigated":[68],"settings":[69],"where":[70,137],"this":[71,130,158],"exploration":[72],"sped-up,":[75],"by":[76],"considering":[77],"analogs":[79],"classical":[81],"environments,":[82,120],"which":[83,144],"then":[85],"queried":[87],"in":[88,98,114,118,200],"superposition.":[89],"If":[90],"environments":[92,105],"have":[93],"strict":[95],"periodic":[96],"structure":[97],"time":[99,199],"(i.e.":[100],"are":[101],"strictly":[102,142],"episodic),":[103],"such":[104,135],"effectively":[108],"converted":[109],"conventional":[111],"oracles":[112],"encountered":[113],"information.":[116],"However,":[117],"general":[119],"we":[121,132,179],"obtain":[122],"scenarios":[123],"that":[124,162,181,203],"generalize":[125],"standard":[126,163],"oracle":[127,149,191,196],"tasks.":[128],"work,":[131],"consider":[133],"one":[134,213],"generalization,":[136],"not":[141],"episodic,":[143],"mapped":[146],"identification":[150,192],"setting":[151],"with":[152,167],"changing":[154],"oracle.":[155],"We":[156],"analyze":[157],"case":[159],"show":[161],"amplitude-amplification":[164],"techniques":[165],"can,":[166],"minor":[168],"modifications,":[169],"still":[170],"applied":[172],"achieve":[174],"quadratic":[175],"speed-ups.":[176],"addition,":[178],"prove":[180],"algorithm":[183],"based":[184],"on":[185],"Grover":[186],"iterations":[187],"optimal":[189],"for":[190],"even":[193],"if":[194],"changes":[197],"over":[198],"way":[202],"\"rewarded":[205],"space\"":[206],"monotonically":[208],"increasing.":[209],"This":[210],"result":[211],"constitutes":[212],"generalizations":[217],"quantum-accessible":[219]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2020-08-10T00:00:00"}
