{"id":"https://openalex.org/W2155044741","doi":"https://doi.org/10.1109/tsmca.2012.2183349","title":"Fusion of Multiple Behaviors Using Layered Reinforcement Learning","display_name":"Fusion of Multiple Behaviors Using Layered Reinforcement Learning","publication_year":2012,"publication_date":"2012-02-21","ids":{"openalex":"https://openalex.org/W2155044741","doi":"https://doi.org/10.1109/tsmca.2012.2183349","mag":"2155044741"},"language":"en","primary_location":{"id":"doi:10.1109/tsmca.2012.2183349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmca.2012.2183349","pdf_url":null,"source":{"id":"https://openalex.org/S4210201610","display_name":"IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans","issn_l":"1083-4427","issn":["1083-4427","1558-2426"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans","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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Electrical Engineering Department, National Sun Yat-sen University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, National Sun Yat-sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731680","display_name":"Yu-Jen Chen","orcid":"https://orcid.org/0000-0003-0288-0796"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jen Chen","raw_affiliation_strings":["Electrical Engineering Department, National Chung Cheng University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, National Chung Cheng University, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044558780","display_name":"Chun-Ju Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Ju Wu","raw_affiliation_strings":["Energy and Environment Research Laboratories, Industrial Technology and Research Institute, Taiwan"],"affiliations":[{"raw_affiliation_string":"Energy and Environment Research Laboratories, Industrial Technology and Research Institute, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061189209"],"corresponding_institution_ids":["https://openalex.org/I142974352"],"apc_list":null,"apc_paid":null,"fwci":1.2844,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84138986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"42","issue":"4","first_page":"999","last_page":"1004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.9965000152587891,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.974399983882904,"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":0.8157581090927124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6959284543991089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6193181872367859},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5568580627441406},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5198941230773926},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5087552666664124},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.487667441368103},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4673987030982971},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46041566133499146},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45686930418014526},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44852086901664734},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44625478982925415},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44089847803115845},{"id":"https://openalex.org/keywords/trimming","display_name":"Trimming","score":0.42135509848594666},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41231244802474976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10956016182899475},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10728815197944641}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8157581090927124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959284543991089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193181872367859},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5568580627441406},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5198941230773926},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5087552666664124},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.487667441368103},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4673987030982971},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46041566133499146},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45686930418014526},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44852086901664734},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44625478982925415},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44089847803115845},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.42135509848594666},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41231244802474976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10956016182899475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10728815197944641},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/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/tsmca.2012.2183349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmca.2012.2183349","pdf_url":null,"source":{"id":"https://openalex.org/S4210201610","display_name":"IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans","issn_l":"1083-4427","issn":["1083-4427","1558-2426"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1559996711","https://openalex.org/W1565175369","https://openalex.org/W1780185704","https://openalex.org/W1968768508","https://openalex.org/W1970074386","https://openalex.org/W2021070595","https://openalex.org/W2045762473","https://openalex.org/W2064306341","https://openalex.org/W2077195478","https://openalex.org/W2097856935","https://openalex.org/W2099618002","https://openalex.org/W2110685572","https://openalex.org/W2117941808","https://openalex.org/W2121863487","https://openalex.org/W2125283600","https://openalex.org/W2132099245","https://openalex.org/W2157918543","https://openalex.org/W4214717370","https://openalex.org/W6633361626","https://openalex.org/W6642630624"],"related_works":["https://openalex.org/W1470425429","https://openalex.org/W4318350883","https://openalex.org/W4319083788","https://openalex.org/W4328134586","https://openalex.org/W4200196661","https://openalex.org/W4205478082","https://openalex.org/W3185179407","https://openalex.org/W1983539893","https://openalex.org/W4281385048","https://openalex.org/W4361795583"],"abstract_inverted_index":{"This":[0,132],"study":[1],"introduces":[2],"a":[3,7,51,73,91,171],"method":[4],"to":[5,9,12,80,139,154],"enable":[6],"robot":[8,83],"learn":[10,140],"how":[11],"perform":[13],"new":[14],"tasks":[15],"through":[16,59,130],"human":[17,39],"demonstration":[18],"and":[19,41],"independent":[20],"practice.":[21],"The":[22,112,143],"proposed":[23],"process":[24],"consists":[25],"of":[26,50,65,86,93,115],"two":[27],"interconnected":[28],"phases;":[29],"in":[30,48,67,170],"the":[31,63,70,82,116,121,127,148,159],"first":[32],"phase,":[33],"state-action":[34],"data":[35],"are":[36,124],"obtained":[37],"from":[38],"demonstrations,":[40],"an":[42],"aggregated":[43],"state":[44],"space":[45],"is":[46,95],"learned":[47,129,149],"terms":[49],"decision":[52],"tree":[53,68,71],"that":[54,76,147],"groups":[55],"similar":[56],"states":[57],"together":[58],"reinforcement":[60],"learning.":[61],"Without":[62],"postprocess":[64],"trimming,":[66],"induction,":[69],"encodes":[72],"control":[74,81],"policy":[75,128],"can":[77,100,166],"be":[78,101],"used":[79],"by":[84,103,158],"means":[85],"repeatedly":[87],"improving":[88],"itself.":[89],"Once":[90],"variety":[92],"behaviors":[94,99,107,119,157],"learned,":[96],"more":[97,168],"elaborate":[98],"generated":[102],"selectively":[104],"organizing":[105],"several":[106],"using":[108,126],"another":[109],"Q-learning":[110,137,161],"algorithm.":[111],"composed":[113],"outputs":[114],"organized":[117,152],"basic":[118,156],"on":[120,163],"motor":[122],"level":[123],"weighted":[125],"Q-learning.":[131],"approach":[133],"uses":[134],"three":[135,160],"diverse":[136],"algorithms":[138,162],"complex":[141],"behaviors.":[142],"experimental":[144],"results":[145],"show":[146],"complicated":[150],"behaviors,":[151],"according":[153],"individual":[155],"different":[164],"levels,":[165],"function":[167],"adaptively":[169],"dynamic":[172],"environment.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}