{"id":"https://openalex.org/W2152730650","doi":"https://doi.org/10.1145/1102256.1102278","title":"Counter example for Q-bucket-brigade under prediction problem","display_name":"Counter example for Q-bucket-brigade under prediction problem","publication_year":2005,"publication_date":"2005-06-25","ids":{"openalex":"https://openalex.org/W2152730650","doi":"https://doi.org/10.1145/1102256.1102278","mag":"2152730650"},"language":"en","primary_location":{"id":"doi:10.1145/1102256.1102278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102256.1102278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th annual workshop on Genetic and evolutionary computation","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/A5006972856","display_name":"Atsushi Wada","orcid":"https://orcid.org/0000-0002-4188-7117"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Atsushi Wada","raw_affiliation_strings":["ATR NIS, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR NIS, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I46980622"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084452161","display_name":"Keiki Takadama","orcid":"https://orcid.org/0009-0007-0916-5505"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiki Takadama","raw_affiliation_strings":["Tokyo Institute of Technology, Nagatsuta-cho, Midori-ku, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Nagatsuta-cho, Midori-ku, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573074","display_name":"Katsunori Shimohara","orcid":"https://orcid.org/0000-0003-3649-7699"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsunori Shimohara","raw_affiliation_strings":["ATR NIS, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR NIS, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I46980622"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006972856"],"corresponding_institution_ids":["https://openalex.org/I46980622"],"apc_list":null,"apc_paid":null,"fwci":0.4388,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75335389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9836999773979187,"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":0.8353384733200073},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6902339458465576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5139212608337402},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.484795480966568},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4713577330112457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41071751713752747},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40962642431259155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3813720941543579},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3516347408294678},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3423503637313843},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1509677767753601},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.12629598379135132}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8353384733200073},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6902339458465576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5139212608337402},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.484795480966568},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4713577330112457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41071751713752747},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40962642431259155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3813720941543579},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3516347408294678},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3423503637313843},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1509677767753601},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.12629598379135132},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1102256.1102278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102256.1102278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th annual workshop on Genetic and evolutionary computation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1505852642","https://openalex.org/W1506349967","https://openalex.org/W1515851193","https://openalex.org/W1516897956","https://openalex.org/W1517718593","https://openalex.org/W1547105496","https://openalex.org/W1646707810","https://openalex.org/W1760373942","https://openalex.org/W1964928737","https://openalex.org/W1965227651","https://openalex.org/W1989101984","https://openalex.org/W1999128321","https://openalex.org/W2073677619","https://openalex.org/W2088618689","https://openalex.org/W2100677568","https://openalex.org/W2107277317","https://openalex.org/W2112483970","https://openalex.org/W2124175081","https://openalex.org/W2125510930","https://openalex.org/W2134367663","https://openalex.org/W2139418546","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2150459019","https://openalex.org/W2152615835","https://openalex.org/W2157838568","https://openalex.org/W2165131254","https://openalex.org/W2169982856","https://openalex.org/W2261323909","https://openalex.org/W2480201967","https://openalex.org/W3011120880","https://openalex.org/W3028232160","https://openalex.org/W4212774754","https://openalex.org/W6678900246"],"related_works":["https://openalex.org/W1517908938","https://openalex.org/W2165272709","https://openalex.org/W2375053028","https://openalex.org/W1981749300","https://openalex.org/W2373502461","https://openalex.org/W1999937375","https://openalex.org/W586558997","https://openalex.org/W3123775475","https://openalex.org/W2295113609","https://openalex.org/W3124598481"],"abstract_inverted_index":{"Aiming":[0],"to":[1,30,73,89,128],"clarify":[2],"the":[3,21,65,75,83,87,92,96,104,108],"convergence":[4],"or":[5,123],"divergence":[6,76,117],"conditions":[7],"for":[8,59],"Learning":[9,48],"Classifier":[10],"System":[11],"(LCS),":[12],"this":[13],"paper":[14],"explores:":[15],"(1)":[16,98],"an":[17],"extreme":[18],"condition":[19],"where":[20,107],"reinforcement":[22,44],"process":[23,45],"of":[24,77],"LCS":[25,60,90,99],"diverges;":[26],"and":[27,46,114],"(2)":[28,115],"methods":[29],"avoid":[31],"such":[32,116],"divergence.":[33],"Based":[34],"on":[35,64],"our":[36],"previous":[37],"work":[38],"that":[39],"showed":[40],"equivalence":[41],"between":[42],"LCS's":[43],"Reinforcement":[47],"(RL)":[49],"with":[50,61,79,100],"Function":[51],"approximation":[52],"(FA)":[53],"method,":[54],"we":[55],"present":[56],"a":[57,69],"counter-example":[58,70,88],"Q-bucket-brigade":[62,101],"based":[63],"11-state":[66],"star":[67],"problem,":[68,106],"originally":[71],"proposed":[72],"show":[74],"Q-learning":[78],"linear":[80],"FA.":[81],"Furthermore,":[82],"empirical":[84],"results":[85,93],"applying":[86,124],"verified":[91],"predicted":[94],"from":[95],"theory:":[97],"diverged":[102],"under":[103],"prediction":[105],"action":[109],"selection":[110],"policy":[111],"was":[112,118],"fixed;":[113],"avoided":[119],"by":[120],"using":[121],"implicit-bucket-brigade":[122],"residual":[125],"gradient":[126],"algorithm":[127],"Q-bucket-brigade.":[129]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
