{"id":"https://openalex.org/W952777547","doi":"https://doi.org/10.1007/s40595-015-0045-x","title":"A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers","display_name":"A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers","publication_year":2015,"publication_date":"2015-07-04","ids":{"openalex":"https://openalex.org/W952777547","doi":"https://doi.org/10.1007/s40595-015-0045-x","mag":"952777547"},"language":"en","primary_location":{"id":"doi:10.1007/s40595-015-0045-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-015-0045-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-015-0045-x.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-015-0045-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032488540","display_name":"Bilal H. Abed-alguni","orcid":"https://orcid.org/0000-0002-7481-4854"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bilal H. Abed-alguni","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","institution_ids":["https://openalex.org/I78757542"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054614441","display_name":"Stephan K. Chalup","orcid":"https://orcid.org/0000-0002-7886-3653"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stephan K. Chalup","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","institution_ids":["https://openalex.org/I78757542"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044442341","display_name":"Frans Henskens","orcid":"https://orcid.org/0000-0003-2358-5630"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Frans A. Henskens","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Newcastle, Callaghan, NSW, 2308, Australia","institution_ids":["https://openalex.org/I78757542"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Newcastle  Callaghan Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089991670","display_name":"David Pa\u00fal","orcid":"https://orcid.org/0000-0002-2428-5667"},"institutions":[{"id":"https://openalex.org/I90745801","display_name":"University of New England","ror":"https://ror.org/04r659a56","country_code":"AU","type":"education","lineage":["https://openalex.org/I90745801"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David J. Paul","raw_affiliation_strings":["School of Science and Technology, University of New England, Armidale, NSW, 2351, Australia","University of Newcastle","University of New England"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, University of New England, Armidale, NSW, 2351, Australia","institution_ids":["https://openalex.org/I90745801"]},{"raw_affiliation_string":"University of Newcastle","institution_ids":[]},{"raw_affiliation_string":"University of New England","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032488540"],"corresponding_institution_ids":["https://openalex.org/I78757542"],"apc_list":null,"apc_paid":null,"fwci":5.3379,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95582951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"4","first_page":"213","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.7242999076843262},{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.68604576587677},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6567674875259399},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6334458589553833},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5872151255607605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549578070640564},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4454796016216278},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44255533814430237},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.42795953154563904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.425799697637558},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.4100739061832428},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.2600361108779907},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18918627500534058},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.1882486343383789},{"id":"https://openalex.org/keywords/teaching-method","display_name":"Teaching method","score":0.12840446829795837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10971832275390625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242999076843262},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.68604576587677},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6567674875259399},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6334458589553833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5872151255607605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549578070640564},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4454796016216278},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44255533814430237},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.42795953154563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.425799697637558},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.4100739061832428},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2600361108779907},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18918627500534058},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.1882486343383789},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.12840446829795837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10971832275390625},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s40595-015-0045-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-015-0045-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-015-0045-x.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/28984739","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:rune.une.edu.au:1959.11/17940","is_oa":false,"landing_page_url":"https://hdl.handle.net/1959.11/17940","pdf_url":null,"source":{"id":"https://openalex.org/S7407055448","display_name":"RUNE (Research UNE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:uon:24397","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.13/1321576","pdf_url":null,"source":{"id":"https://openalex.org/S4306401391","display_name":"NOVA (University of Newcastle, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s40595-015-0045-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-015-0045-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-015-0045-x.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W952777547.pdf","grobid_xml":"https://content.openalex.org/works/W952777547.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W134602879","https://openalex.org/W256201028","https://openalex.org/W1510673313","https://openalex.org/W1537934887","https://openalex.org/W1542132247","https://openalex.org/W1557517019","https://openalex.org/W1578371046","https://openalex.org/W1592847719","https://openalex.org/W1598052524","https://openalex.org/W1650504995","https://openalex.org/W1996625075","https://openalex.org/W2008693313","https://openalex.org/W2033562874","https://openalex.org/W2046756175","https://openalex.org/W2055060379","https://openalex.org/W2063282497","https://openalex.org/W2091387107","https://openalex.org/W2094723835","https://openalex.org/W2101112865","https://openalex.org/W2109910161","https://openalex.org/W2117316169","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2134164581","https://openalex.org/W2143042284","https://openalex.org/W2151116481","https://openalex.org/W2154535830","https://openalex.org/W2156269940","https://openalex.org/W2158548602","https://openalex.org/W2162022118","https://openalex.org/W2270900503","https://openalex.org/W2397962349","https://openalex.org/W2531563875","https://openalex.org/W2569741183","https://openalex.org/W2615995758","https://openalex.org/W2989068617","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4253683673"],"related_works":["https://openalex.org/W2478195092","https://openalex.org/W2740949427","https://openalex.org/W2466909816","https://openalex.org/W2739584557","https://openalex.org/W2993407327","https://openalex.org/W3084279499","https://openalex.org/W3137277498","https://openalex.org/W2738303290","https://openalex.org/W2994076959","https://openalex.org/W2124020042"],"abstract_inverted_index":{"The":[0,31,51,76,112],"hierarchical":[1,38],"organisation":[2],"of":[3,45,82],"distributed":[4,37,118],"systems":[5],"can":[6],"provide":[7],"an":[8,17],"efficient":[9],"decomposition":[10],"for":[11,19,23,108],"machine":[12],"learning.":[13],"This":[14],"paper":[15],"proposes":[16],"algorithm":[18,32,78,113],"cooperative":[20,140],"policy":[21],"construction":[22],"independent":[24],"learners,":[25],"named":[26],"Q-learning":[27,136,141],"with":[28],"aggregation":[29],"(QA-learning).":[30],"is":[33,97],"based":[34],"on":[35],"a":[36,86,106,117,130],"learning":[39],"model":[40],"and":[41,49,73,122,137],"utilises":[42],"three":[43],"specialisations":[44],"agents:":[46],"workers,":[47],"tutors":[48],"consultants.":[50],"consultant":[52],"agent":[53,135],"incorporates":[54],"the":[55,71,80,101,109],"entire":[56,110],"system":[57],"in":[58,105],"its":[59],"problem":[60],"space,":[61],"which":[62],"it":[63],"decomposes":[64],"into":[65,85,100],"sub-problems":[66],"that":[67,126],"are":[68],"assigned":[69],"to":[70,129],"tutor":[72,92],"worker":[74,83],"agents.":[75],"QA-learning":[77,127],"aggregates":[79],"Q-tables":[81],"agents":[84],"central":[87],"repository":[88],"managed":[89],"by":[90],"their":[91],"agent.":[93],"Each":[94],"tutor\u2019s":[95],"Q-table":[96,107],"then":[98],"incorporated":[99],"consultant\u2019s":[102],"Q-table,":[103],"resulting":[104],"problem.":[111],"was":[114],"tested":[115],"using":[116],"hunter":[119],"prey":[120],"problem,":[121],"experimental":[123],"results":[124],"show":[125],"converges":[128],"solution":[131],"faster":[132],"than":[133],"single":[134],"some":[138],"famous":[139],"algorithms.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}