{"id":"https://openalex.org/W2537938292","doi":"https://doi.org/10.1109/iske.2010.5680787","title":"Quantum-inspired reinforcement learning for decision-making of Markovian state transition","display_name":"Quantum-inspired reinforcement learning for decision-making of Markovian state transition","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2537938292","doi":"https://doi.org/10.1109/iske.2010.5680787","mag":"2537938292"},"language":"en","primary_location":{"id":"doi:10.1109/iske.2010.5680787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iske.2010.5680787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5000582423","display_name":"Daoyi Dong","orcid":"https://orcid.org/0000-0002-7425-3559"},"institutions":[{"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/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"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"]}]},{"author_position":"last","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 System Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Department of Control and System Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000582423"],"corresponding_institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.451,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76862897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1443","issue":null,"first_page":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9908999800682068,"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":0.9779999852180481,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9117306470870972},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7120755910873413},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6691718697547913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6389268040657043},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6387580037117004},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.5557917356491089},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5189054608345032},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46189960837364197},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.445472776889801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43789321184158325},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35424476861953735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22176417708396912},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20930424332618713},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.09427955746650696},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08811190724372864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9117306470870972},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7120755910873413},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6691718697547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389268040657043},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6387580037117004},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.5557917356491089},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5189054608345032},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46189960837364197},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.445472776889801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43789321184158325},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35424476861953735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22176417708396912},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20930424332618713},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.09427955746650696},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08811190724372864},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iske.2010.5680787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iske.2010.5680787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1631356911","https://openalex.org/W1965765304","https://openalex.org/W2002372750","https://openalex.org/W2017107529","https://openalex.org/W2032675708","https://openalex.org/W2043353432","https://openalex.org/W2056325504","https://openalex.org/W2063467433","https://openalex.org/W2077969214","https://openalex.org/W2100677568","https://openalex.org/W2101636610","https://openalex.org/W2103343043","https://openalex.org/W2117872989","https://openalex.org/W2117941808","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2128024939","https://openalex.org/W2128609675","https://openalex.org/W2129177996","https://openalex.org/W2130751725","https://openalex.org/W2151331460","https://openalex.org/W2764347725","https://openalex.org/W2913164239","https://openalex.org/W3037585991","https://openalex.org/W3041202696","https://openalex.org/W3101558632","https://openalex.org/W3105001926","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W4400868993","https://openalex.org/W2937181779","https://openalex.org/W2145363145"],"abstract_inverted_index":{"A":[0],"novel":[1],"quantum-inspired":[2],"reinforcement":[3,64],"learning":[4,57],"(QiRL)":[5],"algorithm":[6,17],"is":[7,34,53],"proposed":[8],"for":[9,73],"decision-making":[10,75],"of":[11,46],"Markovian":[12,47],"state":[13,48],"transition.":[14],"The":[15,66],"QiRL":[16,52,67],"adopts":[18],"a":[19],"probabilistic":[20],"action":[21],"selection":[22],"policy":[23],"to":[24,56],"better":[25],"balance":[26],"the":[27,37],"tradeoff":[28],"between":[29],"exploration":[30],"and":[31,59],"exploitation,":[32],"which":[33],"inspired":[35],"by":[36],"collapse":[38],"phenomenon":[39],"in":[40],"quantum":[41],"measurement.":[42],"Several":[43],"simulated":[44],"experiments":[45],"transition":[49],"demonstrate":[50],"that":[51],"more":[54],"robust":[55],"rates":[58],"initial":[60],"states":[61],"than":[62],"traditional":[63],"learning.":[65],"approach":[68],"provides":[69],"an":[70],"effective":[71],"method":[72],"complex":[74],"problems.":[76]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}