{"id":"https://openalex.org/W2064306341","doi":"https://doi.org/10.1163/156855308x344882","title":"Efficient Behavior Learning Based on State Value Estimation of Self and Others","display_name":"Efficient Behavior Learning Based on State Value Estimation of Self and Others","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2064306341","doi":"https://doi.org/10.1163/156855308x344882","mag":"2064306341"},"language":"en","primary_location":{"id":"doi:10.1163/156855308x344882","is_oa":false,"landing_page_url":"https://doi.org/10.1163/156855308x344882","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-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/A5089803467","display_name":"Yasutake Takahashi","orcid":"https://orcid.org/0000-0001-7301-9907"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutake Takahashi","raw_affiliation_strings":["a    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"a    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027347020","display_name":"Kentaro Noma","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Noma","raw_affiliation_strings":["b    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"b    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044985800","display_name":"Minoru Asada","orcid":"https://orcid.org/0000-0001-9506-6333"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minoru Asada","raw_affiliation_strings":["c    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"c    Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":1.7512,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87516854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":"12","first_page":"1379","last_page":"1395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9588000178337097,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9559999704360962,"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":0.8027254343032837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6231096982955933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.605417013168335},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5831558108329773},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5131621956825256},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5047451257705688},{"id":"https://openalex.org/keywords/teamwork","display_name":"Teamwork","score":0.4356766641139984},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43218743801116943},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.42636823654174805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1689998209476471}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8027254343032837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6231096982955933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605417013168335},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5831558108329773},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5131621956825256},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5047451257705688},{"id":"https://openalex.org/C111226992","wikidata":"https://www.wikidata.org/wiki/Q626225","display_name":"Teamwork","level":2,"score":0.4356766641139984},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43218743801116943},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.42636823654174805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1689998209476471},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1163/156855308x344882","is_oa":false,"landing_page_url":"https://doi.org/10.1163/156855308x344882","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.539.4280","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.539.4280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.er.ams.eng.osaka-u.ac.jp/Paper/2008/Takahashi08g.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1565175369","https://openalex.org/W1607817625","https://openalex.org/W2012036715","https://openalex.org/W2121863487","https://openalex.org/W2128421316","https://openalex.org/W2131829828","https://openalex.org/W2133040789","https://openalex.org/W2134972977","https://openalex.org/W2141754131","https://openalex.org/W2150149497","https://openalex.org/W2150884987","https://openalex.org/W2155791599","https://openalex.org/W2160913278","https://openalex.org/W2168342951","https://openalex.org/W2233997862","https://openalex.org/W2913060459","https://openalex.org/W4248367297"],"related_works":["https://openalex.org/W2045236383","https://openalex.org/W2121778218","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W1537934887","https://openalex.org/W3173185086","https://openalex.org/W3103643887","https://openalex.org/W2094557321","https://openalex.org/W1483574046","https://openalex.org/W4362598698"],"abstract_inverted_index":{"The":[0,79,109,177],"existing":[1],"reinforcement":[2],"learning":[3,56,64,192,211],"methods":[4],"have":[5],"been":[6],"seriously":[7],"suffering":[8],"from":[9,121],"the":[10,13,27,63,84,101,104,113,118,122,126,133,136,141,144,167,174,191,197,202],"curse":[11],"of":[12,26,33,54,103,112,117,135,143,196],"dimension":[14],"problem,":[15],"especially":[16],"when":[17],"they":[18],"are":[19,86,129],"applied":[20,180],"to":[21,82,99,131,146,152,172,181],"multiagent":[22,59],"dynamic":[23],"environments.":[24],"One":[25],"typical":[28],"examples":[29],"is":[30,97,150,156,179],"a":[31,52,58,90,163,182],"case":[32],"RoboCup":[34],"competitions":[35],"since":[36],"other":[37],"agents":[38],"and":[39,45,73,106,125,160,190,206],"their":[40],"behavior":[41,69,75],"easily":[42],"cause":[43],"state":[44,110,119,142,164,170],"action":[46,107,138],"space":[47,111,171],"variations.":[48],"This":[49],"paper":[50],"presents":[51],"method":[53,178],"modular":[55],"in":[57,166],"environment":[60],"by":[61,158],"which":[62],"agent":[65,193],"can":[66],"acquire":[67],"cooperative":[68],"with":[70,94],"its":[71,77,153],"teammates":[72],"competitive":[74],"against":[76],"opponents.":[78],"key":[80],"ideas":[81],"resolve":[83],"issue":[85],"as":[87,162],"follows.":[88],"First,":[89],"two-layer":[91],"hierarchical":[92],"system":[93],"multilearning":[95],"modules":[96],"adopted":[98],"reduce":[100,132],"size":[102,134],"sensor":[105],"spaces.":[108],"top":[114,168],"layer":[115,169],"consists":[116],"values":[120],"lower":[123],"level":[124],"macro":[127],"actions":[128],"used":[130,161],"physical":[137],"space.":[139],"Second,":[140],"other,":[145],"what":[147],"extent":[148],"it":[149],"close":[151],"own":[154],"goal,":[155],"estimated":[157],"observation":[159],"variable":[165],"realize":[173],"cooperative/competitive":[175],"behavior.":[176],"four":[183],"(defense":[184],"team)-on-five":[185],"(offense":[186],"team)":[187,199],"game":[188],"task":[189],"(a":[194],"passer":[195],"offense":[198],"successfully":[200],"acquired":[201],"teamwork":[203],"plays":[204],"(pass":[205],"shoot)":[207],"within":[208],"much":[209],"shorter":[210],"time.":[212]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"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"}