{"id":"https://openalex.org/W2967845823","doi":"https://doi.org/10.1109/cec.2019.8790115","title":"XCS with Combined Reward Method (XCSCR) for Policy Search in Multistep Problems","display_name":"XCS with Combined Reward Method (XCSCR) for Policy Search in Multistep Problems","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2967845823","doi":"https://doi.org/10.1109/cec.2019.8790115","mag":"2967845823"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2019.8790115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","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/A5063244017","display_name":"Zheming Zhang","orcid":"https://orcid.org/0000-0002-9273-4583"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zheming Zhang","raw_affiliation_strings":["Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065533636","display_name":"Will N. Browne","orcid":"https://orcid.org/0000-0001-8979-2224"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Will N. Browne","raw_affiliation_strings":["Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089501127","display_name":"Dale A. Carnegie","orcid":null},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Dale A. Carnegie","raw_affiliation_strings":["Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41156924"],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.38946024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2982","last_page":"2989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9876999855041504,"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":0.9771000146865845,"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":0.8020083904266357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.686873197555542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868426561355591},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5696920156478882},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5380463600158691},{"id":"https://openalex.org/keywords/stimulus","display_name":"Stimulus (psychology)","score":0.5101652145385742},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4887787997722626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42839616537094116},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41676026582717896},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.2070913016796112},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17640870809555054}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8020083904266357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686873197555542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868426561355591},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5696920156478882},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5380463600158691},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.5101652145385742},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4887787997722626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42839616537094116},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41676026582717896},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2070913016796112},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17640870809555054},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec.2019.8790115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W100322028","https://openalex.org/W1601079897","https://openalex.org/W1989101984","https://openalex.org/W1995663008","https://openalex.org/W2045031658","https://openalex.org/W2048984163","https://openalex.org/W2051228319","https://openalex.org/W2052153221","https://openalex.org/W2084028892","https://openalex.org/W2134367663","https://openalex.org/W2567015638","https://openalex.org/W2580175322","https://openalex.org/W2897170223","https://openalex.org/W3103559770","https://openalex.org/W4250109829","https://openalex.org/W4297795161","https://openalex.org/W6703627465","https://openalex.org/W6731334075","https://openalex.org/W6732665253"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W2382997850","https://openalex.org/W4391331176","https://openalex.org/W2586732548"],"abstract_inverted_index":{"A":[0,122,155,172],"reward":[1,17,71,94,124],"mechanism":[2,18,125,142,158,175],"is":[3],"critical":[4],"for":[5,43,52,101,133,180,223],"a":[6,20,31,92],"Reinforcement":[7],"Learning":[8,86],"agent":[9,131],"to":[10,30,76,97,198],"learn":[11,77],"action":[12],"policies":[13,78,104,134,197,211],"from":[14,35],"rewards.":[15,138],"The":[16,109,220],"establishes":[19],"policy":[21,29,46,168,225],"by":[22],"estimating":[23],"contributions":[24],"of":[25,27,128,147,162,194],"constituents":[26],"the":[28,45,61,99,129,144,160,167,192,204,208,224],"reward.":[32],"Traditionally,":[33],"rewards":[34,42,51,57,115,149,165],"an":[36,84,177],"environment":[37],"have":[38],"two":[39],"categories:":[40],"long-term":[41,112,163],"guiding":[44],"learning":[47,63,173,207],"process,":[48],"and":[49,113,152,213],"short-term":[50,114,123,137],"optimisation.":[53],"However,":[54],"long-term,":[55],"positive":[56,164],"are":[58],"scarce":[59],"at":[60],"initial":[62],"phase":[64],"in":[65,105,166,185],"multistep":[66,106],"problems":[67],"such":[68],"that":[69,203],"existing":[70],"mechanisms":[72],"lack":[73],"sufficient":[74],"stimulus":[75],"effectively.":[79],"This":[80],"paper":[81],"proposes":[82],"XCSCR,":[83],"Accuracy-based":[85],"Classifier":[87],"System":[88],"(XCS)":[89],"algorithm":[90],"with":[91],"combined":[93],"(CR)":[95],"method,":[96],"guide":[98],"search":[100,226],"global":[102],"optimal":[103],"maze":[107,187],"problems.":[108],"XCSCR":[110,195,205],"discriminates":[111],"through":[116],"four":[117],"novel":[118],"rewardassignment":[119],"mechanisms:":[120],"1)":[121],"encourages":[126],"exploration":[127,151],"RL":[130],"searching":[132,169],"based":[135],"on":[136,196],"2)":[139],"An":[140],"imprinting":[141],"amends":[143],"negative":[145],"impact":[146,161],"indiscriminate":[148],"between":[150],"exploitation.":[153],"3)":[154],"learning-rate":[156],"switching":[157],"emphasises":[159],"process.":[170],"4)":[171],"step-threshold":[174],"creates":[176],"optimisation":[178],"pressure":[179],"policies.":[181],"Experiments":[182],"were":[183],"conducted":[184],"three":[186],"environments":[188],"as":[189],"this":[190],"enabled":[191],"effects":[193],"interpreted":[199],"easily.":[200],"Results":[201],"show":[202],"enables":[206],"optimum":[209],"path-finding":[210],"quicker":[212],"more":[214],"often":[215],"than":[216],"previous":[217],"XCS":[218],"algorithms.":[219],"XCSCR's":[221],"improvements":[222],"will":[227],"facilitate":[228],"realworld":[229],"applications,":[230],"e.g.":[231],"robotic":[232],"applications.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}