{"id":"https://openalex.org/W2136617285","doi":"https://doi.org/10.1109/icsmc.2007.4414024","title":"Aggregation of tiling-based reinforcement learning algorithms","display_name":"Aggregation of tiling-based reinforcement learning algorithms","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2136617285","doi":"https://doi.org/10.1109/icsmc.2007.4414024","mag":"2136617285"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2007.4414024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4414024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Ju Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, ONT, Canada",", University of Waterloo, Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":", University of Waterloo, Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","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, ONT, Canada",", University of Waterloo, Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":", University of Waterloo, Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1612","last_page":"1617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9940000176429749,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9919000267982483,"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":0.9230049848556519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7970519065856934},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6185961365699768},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.513172447681427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4980812072753906},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.476968377828598},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4729708731174469},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.47170400619506836},{"id":"https://openalex.org/keywords/competitive-learning","display_name":"Competitive learning","score":0.4455564022064209},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4336026906967163},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41759270429611206},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.39894989132881165}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9230049848556519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970519065856934},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6185961365699768},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.513172447681427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4980812072753906},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.476968377828598},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4729708731174469},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.47170400619506836},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.4455564022064209},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4336026906967163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41759270429611206},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.39894989132881165},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2007.4414024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4414024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1495978126","https://openalex.org/W1534355532","https://openalex.org/W1590984588","https://openalex.org/W1987187457","https://openalex.org/W1993740947","https://openalex.org/W2016648380","https://openalex.org/W2055178087","https://openalex.org/W2085130511","https://openalex.org/W2102734279","https://openalex.org/W2109330238","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2126297944","https://openalex.org/W2169022337","https://openalex.org/W2911283634","https://openalex.org/W4214717370","https://openalex.org/W6635608233","https://openalex.org/W6676422638"],"related_works":["https://openalex.org/W2160366419","https://openalex.org/W2590565095","https://openalex.org/W3203657119","https://openalex.org/W4286952720","https://openalex.org/W3042291365","https://openalex.org/W2096837800","https://openalex.org/W3183560647","https://openalex.org/W2057778272","https://openalex.org/W44416870","https://openalex.org/W1645058248"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,5,35,44,53,60,69,105,115],"(RL)":[2],"is":[3,28,37,90],"a":[4,49,85,121],"technique":[6],"that":[7,110],"learns":[8],"an":[9],"optimal":[10,68],"policy":[11],"in":[12],"case":[13],"of":[14,21,64,80,100,120],"knowing":[15],"almost":[16],"nothing":[17],"about":[18],"the":[19,22,34,67,78,93,98,114,118],"dynamics":[20],"environment":[23],"under":[24],"consideration.":[25],"When":[26],"RL":[27,41,123],"combined":[29],"with":[30,97],"function":[31],"approximation":[32],"schemes,":[33,73],"performance":[36,116],"greatly":[38],"influenced":[39],"by":[40],"algorithms":[42],"and":[43,54,104],"parameters.":[45,106],"This":[46,88],"paper":[47],"proposes":[48],"new":[50],"on-line":[51],"multiple":[52,58],"aggregating":[55],"architecture,":[56],"\"aggregated":[57],"reinforcement":[59],"system":[61],"(AMRLS)\".":[62],"Instead":[63],"searching":[65],"for":[66],"parameters":[70],"or":[71],"featurization":[72],"AMRLS":[74,111],"attempts":[75],"to":[76,83],"aggregate":[77],"outcomes":[79],"different":[81],"learners":[82],"produce":[84],"better":[86],"policy.":[87],"architecture":[89],"tested":[91],"on":[92],"mountain":[94],"car":[95],"problem":[96],"aggregation":[99],"several":[101],"related":[102],"tiling":[103],"Experimental":[107],"results":[108],"show":[109],"can":[112],"improve":[113],"over":[117],"use":[119],"single":[122],"algorithm.":[124]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
