{"id":"https://openalex.org/W2072164538","doi":"https://doi.org/10.1142/s0218213006002990","title":"AGGREGATION OF MULTIPLE REINFORCEMENT LEARNING ALGORITHMS","display_name":"AGGREGATION OF MULTIPLE REINFORCEMENT LEARNING ALGORITHMS","publication_year":2006,"publication_date":"2006-10-01","ids":{"openalex":"https://openalex.org/W2072164538","doi":"https://doi.org/10.1142/s0218213006002990","mag":"2072164538"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213006002990","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213006002990","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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/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 University of Waterloo, Waterloo, ON, Canada","[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, 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":"MOHAMED S. KAMEL","raw_affiliation_strings":["Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada","[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, 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 University of Waterloo, Waterloo, ON, Canada","[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, 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":2.3577941,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89534758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"05","first_page":"855","last_page":"861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.998199999332428,"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":0.998199999332428,"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/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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9926999807357788,"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":0.8937418460845947},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.868633508682251},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.6364232897758484},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.580385684967041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5748589038848877},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.5673428177833557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5234783887863159},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47753798961639404},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4600297212600708},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4277060031890869},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.42242228984832764},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41038748621940613},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.1337122917175293},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.11778202652931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8937418460845947},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.868633508682251},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.6364232897758484},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.580385684967041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5748589038848877},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.5673428177833557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5234783887863159},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47753798961639404},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4600297212600708},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4277060031890869},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.42242228984832764},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41038748621940613},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.1337122917175293},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.11778202652931213},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213006002990","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213006002990","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1590984588","https://openalex.org/W2011277999","https://openalex.org/W2091565802","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2141650360","https://openalex.org/W2150884987"],"related_works":["https://openalex.org/W3196155444","https://openalex.org/W4205569898","https://openalex.org/W2171128163","https://openalex.org/W4310801741","https://openalex.org/W3042291365","https://openalex.org/W4321844043","https://openalex.org/W2171968955","https://openalex.org/W155730701","https://openalex.org/W2143680741","https://openalex.org/W3210156800"],"abstract_inverted_index":{"Reinforcement":[0,44],"learning":[1,24,40,55,68,102,107,111],"(RL)":[2],"has":[3],"been":[4],"successfully":[5],"used":[6],"in":[7,53],"many":[8],"fields.":[9],"With":[10],"the":[11],"increasing":[12],"complexity":[13],"of":[14],"environments":[15],"and":[16,85,93,104],"tasks,":[17],"it":[18],"is":[19],"difficult":[20],"for":[21],"a":[22,37,75],"single":[23],"algorithm":[25],"to":[26,57],"cope":[27],"with":[28,31],"complicated":[29],"problems":[30],"high":[32],"performance.":[33],"This":[34,70],"paper":[35],"proposes":[36],"new":[38],"multiple":[39],"architecture,":[41],"\"Aggregated":[42],"Multiple":[43],"Learning":[45],"System":[46],"(AMRLS)\",":[47],"which":[48],"aggregates":[49],"different":[50],"RL":[51],"algorithms":[52],"each":[54],"step":[56],"make":[58],"more":[59,100],"appropriate":[60],"sequential":[61],"decisions":[62],"than":[63,109],"those":[64],"made":[65],"by":[66],"individual":[67,110],"algorithms.":[69,112],"architecture":[71],"was":[72],"tested":[73],"on":[74],"Cart-Pole":[76],"system.":[77],"The":[78],"presented":[79],"simulation":[80],"results":[81],"confirm":[82],"our":[83],"prediction":[84],"reveal":[86],"that":[87],"aggregation":[88],"not":[89],"only":[90],"provides":[91],"robustness":[92],"fault":[94],"tolerance":[95],"ability,":[96],"but":[97],"also":[98],"produces":[99],"smooth":[101],"curves":[103],"needs":[105],"fewer":[106],"steps":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}