{"id":"https://openalex.org/W2002894942","doi":"https://doi.org/10.1109/bicta.2010.5645345","title":"A dynamical policy search model for matching law","display_name":"A dynamical policy search model for matching law","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2002894942","doi":"https://doi.org/10.1109/bicta.2010.5645345","mag":"2002894942"},"language":"en","primary_location":{"id":"doi:10.1109/bicta.2010.5645345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bicta.2010.5645345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109998174","display_name":"Cheng Zhenbo","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhenbo","raw_affiliation_strings":["State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, 100084, China","State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory of Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, China","Information and Engineering College, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory of Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information and Engineering College, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":null,"display_name":"Deng Zhidong","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Zhidong","raw_affiliation_strings":["State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, 100084, China","Information and Engineering College, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information and Engineering College, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9115999937057495,"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/matching","display_name":"Matching (statistics)","score":0.822279155254364},{"id":"https://openalex.org/keywords/matching-law","display_name":"Matching law","score":0.8193316459655762},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5812627077102661},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5568241477012634},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5527846813201904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5445317625999451},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5048523545265198},{"id":"https://openalex.org/keywords/optimal-matching","display_name":"Optimal matching","score":0.4862119257450104},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4817757308483124},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.421358585357666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3115604519844055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2665032744407654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25444692373275757},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10023736953735352}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.822279155254364},{"id":"https://openalex.org/C2781384469","wikidata":"https://www.wikidata.org/wiki/Q6786277","display_name":"Matching law","level":3,"score":0.8193316459655762},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5812627077102661},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5568241477012634},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5527846813201904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5445317625999451},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5048523545265198},{"id":"https://openalex.org/C123853557","wikidata":"https://www.wikidata.org/wiki/Q7098946","display_name":"Optimal matching","level":3,"score":0.4862119257450104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4817757308483124},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.421358585357666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3115604519844055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2665032744407654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25444692373275757},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10023736953735352},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bicta.2010.5645345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bicta.2010.5645345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1575130825","https://openalex.org/W1988505801","https://openalex.org/W2019310225","https://openalex.org/W2062444449","https://openalex.org/W2112439305","https://openalex.org/W2121863487","https://openalex.org/W2135886642","https://openalex.org/W2145190228","https://openalex.org/W2168359464","https://openalex.org/W2172030907"],"related_works":["https://openalex.org/W1978657374","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W1540839255","https://openalex.org/W2002894942"],"abstract_inverted_index":{"The":[0],"matching":[1,31,51,83,109,121,160],"law":[2,84,110,122],"states":[3],"that":[4,22,36,97,120,139],"the":[5,15,25,30,40,50,55,62,65,78,88,98,127,147,156,159,163],"fraction":[6,16],"of":[7,17,64,114,149,165],"choices":[8],"made":[9],"to":[10,82,107,130],"any":[11],"option":[12],"will":[13,38],"match":[14],"total":[18],"rewards":[19],"earned":[20,27],"from":[21,28,87],"option.":[23],"However,":[24],"income":[26],"conducting":[29],"behavior":[32,52,100,142,161],"does":[33,143],"not":[34,144],"imply":[35],"it":[37],"get":[39],"optimal":[41,56,73,89,166],"reward.":[42,152],"It":[43],"is":[44,75,85,105],"unclear":[45],"why":[46],"subjects":[47],"frequently":[48],"exhibit":[49],"rather":[53],"than":[54],"behavior.":[57],"In":[58],"this":[59],"study,":[60],"on":[61],"basis":[63],"policy":[66,79,167],"search":[67],"model":[68],"in":[69,111],"reinforcement":[70],"learning,":[71],"an":[72],"algorithm":[74,80,104,164],"proposed,":[76],"and":[77,93,162],"leading":[81],"derived":[86],"algorithm.":[90],"Theoretical":[91],"analysis":[92],"simulation":[94],"results":[95,118,154],"show":[96],"decision":[99],"achieved":[101],"by":[102],"our":[103],"able":[106],"reach":[108],"many":[112],"kinds":[113],"reward":[115],"schedules.":[116],"Our":[117],"indicate":[119],"can":[123],"be":[124],"exhibited":[125],"whenever":[126],"subject":[128],"tries":[129],"maximize":[131],"a":[132,136],"value":[133],"function":[134],"under":[135],"simple":[137],"assumption":[138],"past":[140],"choice":[141],"care":[145],"about":[146],"values":[148],"future":[150],"long-run":[151],"This":[153],"unveil":[155],"relationships":[157],"between":[158],"search.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}