{"id":"https://openalex.org/W3130292943","doi":"https://doi.org/10.1109/tcyb.2021.3053414","title":"Deep Reinforcement Learning With Quantum-Inspired Experience Replay","display_name":"Deep Reinforcement Learning With Quantum-Inspired Experience Replay","publication_year":2021,"publication_date":"2021-02-20","ids":{"openalex":"https://openalex.org/W3130292943","doi":"https://doi.org/10.1109/tcyb.2021.3053414","mag":"3130292943","pmid":"https://pubmed.ncbi.nlm.nih.gov/33600343"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3053414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3053414","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101645169","display_name":"Qing Wei","orcid":"https://orcid.org/0000-0002-2860-9198"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Wei","raw_affiliation_strings":["Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091591096","display_name":"Hailan Ma","orcid":"https://orcid.org/0000-0002-5039-9916"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Hailan Ma","raw_affiliation_strings":["Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000582423","display_name":"Daoyi Dong","orcid":"https://orcid.org/0000-0002-7425-3559"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daoyi Dong","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101645169"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":10.3457,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.98551164,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"52","issue":"9","first_page":"9326","last_page":"9338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9962999820709229,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8272113800048828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7081481218338013},{"id":"https://openalex.org/keywords/depreciation","display_name":"Depreciation (economics)","score":0.5531821250915527},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.5326648950576782},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4832821190357208},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4330797791481018},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.4210730791091919},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41884875297546387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836210072040558},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17743182182312012}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8272113800048828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081481218338013},{"id":"https://openalex.org/C95383336","wikidata":"https://www.wikidata.org/wiki/Q4198710","display_name":"Depreciation (economics)","level":5,"score":0.5531821250915527},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.5326648950576782},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4832821190357208},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4330797791481018},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.4210730791091919},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41884875297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836210072040558},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17743182182312012},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C58202505","wikidata":"https://www.wikidata.org/wiki/Q5035700","display_name":"Capital formation","level":4,"score":0.0},{"id":"https://openalex.org/C2776943663","wikidata":"https://www.wikidata.org/wiki/Q165687","display_name":"Human capital","level":2,"score":0.0},{"id":"https://openalex.org/C44750222","wikidata":"https://www.wikidata.org/wiki/Q1897397","display_name":"Financial capital","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2021.3053414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3053414","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:33600343","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33600343","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":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1283425618","display_name":null,"funder_award_id":"2018AAA0101100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2172947564","display_name":null,"funder_award_id":"71732003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3174144325","display_name":null,"funder_award_id":"DP190101566","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7231535994","display_name":null,"funder_award_id":"61828303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W14334640","https://openalex.org/W41554520","https://openalex.org/W1529944915","https://openalex.org/W1589747210","https://openalex.org/W1646707810","https://openalex.org/W1988369744","https://openalex.org/W1993118579","https://openalex.org/W1994630055","https://openalex.org/W1996625075","https://openalex.org/W2022508996","https://openalex.org/W2052688942","https://openalex.org/W2059836092","https://openalex.org/W2063756240","https://openalex.org/W2069563009","https://openalex.org/W2117302943","https://openalex.org/W2117941808","https://openalex.org/W2119333483","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2160815625","https://openalex.org/W2161308859","https://openalex.org/W2168676717","https://openalex.org/W2342792901","https://openalex.org/W2419175238","https://openalex.org/W2521267242","https://openalex.org/W2559394418","https://openalex.org/W2580674237","https://openalex.org/W2584269746","https://openalex.org/W2586823359","https://openalex.org/W2746553466","https://openalex.org/W2792315573","https://openalex.org/W2793798239","https://openalex.org/W2802164917","https://openalex.org/W2803973384","https://openalex.org/W2804031762","https://openalex.org/W2883862648","https://openalex.org/W2907281518","https://openalex.org/W2910726239","https://openalex.org/W2943430238","https://openalex.org/W2955251534","https://openalex.org/W2990961515","https://openalex.org/W2998202787","https://openalex.org/W2999912861","https://openalex.org/W3004965358","https://openalex.org/W3099734242","https://openalex.org/W3148685027","https://openalex.org/W6679436768","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6736942654","https://openalex.org/W6747473740","https://openalex.org/W6753199549","https://openalex.org/W6758182352"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4245734937","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"In":[0,21,68,90],"this":[1,91],"article,":[2],"a":[3,62],"novel":[4],"training":[5,150],"paradigm":[6],"inspired":[7],"by":[8],"quantum":[9,75],"computation":[10],"is":[11,114,153],"proposed":[12,32],"for":[13],"deep":[14],"reinforcement":[15],"learning":[16],"(DRL)":[17],"with":[18,34,148],"experience":[19,26,36,56],"replay.":[20],"contrast":[22],"to":[23,47,60,118,156],"the":[24,31,43,48,51,79,88,93,97,100,105,108,111,120,123],"traditional":[25],"replay":[27,37,44],"mechanism":[28],"in":[29,74],"DRL,":[30],"DRL":[33,159],"quantum-inspired":[35],"(DRL-QER)":[38],"adaptively":[39],"chooses":[40],"experiences":[41],"from":[42],"buffer":[45],"according":[46],"complexity":[49],"and":[50,66,77,82,104,141,152,164],"replayed":[52],"times":[53],"of":[54,107,122,145],"each":[55],"(also":[57],"called":[58],"transition),":[59],"achieve":[61],"balance":[63],"between":[64,99],"exploration":[65],"exploitation.":[67],"DRL-QER,":[69],"transitions":[70],"are":[71,85],"first":[72],"formulated":[73],"representations":[76],"then":[78],"preparation":[80,94],"operation":[81,84,95,113],"depreciation":[83,112],"performed":[86],"on":[87,128,143],"transitions.":[89,124],"process,":[92],"reflects":[96],"relationship":[98],"temporal-difference":[101],"errors":[102],"(TD-errors)":[103],"importance":[106],"experiences,":[109],"while":[110],"taken":[115],"into":[116],"account":[117],"ensure":[119],"diversity":[121],"The":[125],"experimental":[126],"results":[127],"Atari":[129],"2600":[130],"games":[131,147],"show":[132],"that":[133],"DRL-QER":[134],"outperforms":[135],"state-of-the-art":[136],"algorithms,":[137],"such":[138,157],"as":[139,161],"DRL-PER":[140],"DCRL":[142],"most":[144],"these":[146],"improved":[149],"efficiency":[151],"also":[154],"applicable":[155],"memory-based":[158],"approaches":[160],"double":[162],"network":[163],"dueling":[165],"network.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}