{"id":"https://openalex.org/W2141650360","doi":"https://doi.org/10.1109/icsmc.2004.1399805","title":"Reinforcement learning and aggregation","display_name":"Reinforcement learning and aggregation","publication_year":2005,"publication_date":"2005-03-31","ids":{"openalex":"https://openalex.org/W2141650360","doi":"https://doi.org/10.1109/icsmc.2004.1399805","mag":"2141650360"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1399805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1399805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5057515922","display_name":"Ju Jiang","orcid":"https://orcid.org/0000-0002-0700-8035"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ju Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039318050","display_name":"Mohamed S. Kamel","orcid":"https://orcid.org/0000-0001-6173-8082"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"M. Kamel","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046216474","display_name":"Liang-Bi Chen","orcid":"https://orcid.org/0000-0003-3181-4480"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Department of Systems Design, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057515922"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.755,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8753064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1303","last_page":"1308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9785000085830688,"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":0.9763000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8915209770202637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6989059448242188},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6954249143600464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.678680419921875},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5464076995849609},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5131538510322571},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46824729442596436},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4288228750228882},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25167232751846313}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8915209770202637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6989059448242188},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6954249143600464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.678680419921875},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5464076995849609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5131538510322571},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46824729442596436},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4288228750228882},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25167232751846313},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icsmc.2004.1399805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1399805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-99958","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-99958","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-99958","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=2&rft.issue=&rft.date=2004&rft.spage=1303&rft.aulast=Jiang&rft.aufirst=Ju%7C&rft.atitle=Reinforcement%20learning%20and%20aggregation&rft.title=ConferencProceedings%20-%20IEEE%20International%20Conference%20on%20Systems%2C%20Man%20and%20Cybernetics","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1480676279","https://openalex.org/W1590984588","https://openalex.org/W1641379095","https://openalex.org/W1681475672","https://openalex.org/W1982678075","https://openalex.org/W2041367235","https://openalex.org/W2044676734","https://openalex.org/W2055178087","https://openalex.org/W2062472030","https://openalex.org/W2091565802","https://openalex.org/W2102734279","https://openalex.org/W2107726111","https://openalex.org/W2113998737","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2152610444","https://openalex.org/W2471081794","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W6635608233","https://openalex.org/W6677347465","https://openalex.org/W6720804594"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1966456942","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3127551068","https://openalex.org/W2808546214","https://openalex.org/W2152445738","https://openalex.org/W225045806"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,5,12,71,77,107,135,150,193],"(RL)":[2],"is":[3,25,73,89,130,136,153,169],"a":[4,9,92,138,162],"technique":[6],"that":[7,178],"provides":[8],"means":[10],"for":[11],"an":[13,146],"optimal":[14,115],"control":[15],"policy":[16],"when":[17],"the":[18,21,70,84,110,114,128,132,144,158,173,188,192,196,200],"dynamics":[19],"of":[20,83,86,91,122,134,198],"environment":[22,160,168],"under":[23],"consideration":[24],"unavailable":[26],"[L.P.":[27],"Kaelbling":[28],"et":[29,53,67],"al.,":[30,54,68],"1996,":[31],"R.S.":[32],"Sutton":[33],"and":[34,58,79,95,113,124,184,195],"A.G.":[35],"Barto,":[36],"1998].":[37],"While":[38],"RL":[39,87,159],"has":[40],"been":[41],"successfully":[42],"applied":[43],"in":[44,98,106,120],"many":[45],"single":[46],"or":[47],"multiple":[48],"agents":[49],"systems":[50],"[S.":[51],"Arai":[52],"2000,":[55,61],"H.R.":[56],"Berenji":[57],"D.A.":[59],"Vengerov,":[60],"M.":[62],"Tan,":[63],"1993,":[64],"Y.":[65],"Nagayuki":[66],"2000],":[69],"quality":[72],"greatly":[74],"influenced":[75],"by":[76],"algorithms":[78,88],"their":[80],"parameters.":[81],"Setting":[82],"parameters":[85,100,116],"something":[90],"black":[93],"art,":[94],"small":[96],"differences":[97,105],"these":[99],"can":[101,117],"lead":[102],"to":[103,142,155,171],"large":[104],"qualities.":[108],"Determining":[109],"best":[111],"algorithm":[112],"be":[118],"costly":[119],"terms":[121],"time":[123],"computation.":[125],"Even":[126],"if":[127],"cost":[129],"acceptable,":[131],"robustness":[133],"still":[137],"question.":[139],"In":[140],"order":[141],"address":[143],"difficulty,":[145],"aggregated":[147],"multiagent":[148,163],"reinforcement":[149],"system":[151],"(AMRLS)":[152],"proposed":[154],"deal":[156],"with":[157,180],"as":[161],"environment.":[164],"A":[165],"maze":[166],"world":[167],"used":[170],"validate":[172],"AMRLS.":[174],"Experimental":[175],"results":[176],"illustrate":[177],"compared":[179],"normal":[181],"Q(/spl":[182],"lambda/)-learning":[183],"SARSA(/spl":[185],"lambda/)":[186],"algorithms,":[187],"AMRLS":[189],"increases":[190],"both":[191],"speed":[194],"rate":[197],"reaching":[199],"shortest":[201],"path.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}