{"id":"https://openalex.org/W2289410116","doi":null,"title":"A framework for aggregation of multiple reinforcement learning algorithms","display_name":"A framework for aggregation of multiple reinforcement learning algorithms","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2289410116","mag":"2289410116"},"language":"en","primary_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/2752","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/2752","pdf_url":"http://hdl.handle.net/10012/2752","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10012/2752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057515922","display_name":"Ju Jiang","orcid":"https://orcid.org/0000-0002-0700-8035","observed_orcids":["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":["University of Waterloo , Canada"],"raw_orcid":"https://orcid.org/0000-0002-0700-8035","affiliations":[{"raw_affiliation_string":"University of Waterloo , Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057515922"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.5170000195503235},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.9599999785423279},{"id":"https://openalex.org/keywords/value-function-learning","display_name":"value function learning","score":0.7730000019073486},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.9610000252723694},{"id":"https://openalex.org/keywords/direct-policy-search","display_name":"direct policy search","score":0.8539999723434448},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"genetic algorithm","score":0.7710000276565552},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.453000009059906},{"id":"https://openalex.org/keywords/algorithm-selection","display_name":"algorithm selection","score":0.3050000071525574},{"id":"https://openalex.org/keywords/cart-pole-balancing","display_name":"cart-pole balancing","score":0.6850000023841858},{"id":"https://openalex.org/keywords/mountain-car-problem","display_name":"mountain car problem","score":0.7409999966621399},{"id":"https://openalex.org/keywords/flight-control","display_name":"flight control","score":0.7950000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8834549188613892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870630025863647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071448922157288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.541117787361145},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5147535800933838},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43758127093315125},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/2752","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/2752","pdf_url":"http://hdl.handle.net/10012/2752","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},{"id":"mag:2289410116","doi":null,"is_oa":false,"landing_page_url":"https://uwspace.uwaterloo.ca/bitstream/10012/2752/1/JuThesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/2752","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/2752","pdf_url":"http://hdl.handle.net/10012/2752","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2289410116.pdf","grobid_xml":"https://content.openalex.org/works/W2289410116.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W1901460","https://openalex.org/W54221576","https://openalex.org/W142858861","https://openalex.org/W145683767","https://openalex.org/W162989097","https://openalex.org/W1495978126","https://openalex.org/W1497256448","https://openalex.org/W1508229132","https://openalex.org/W1512947503","https://openalex.org/W1519614353","https://openalex.org/W1523950537","https://openalex.org/W1534175858","https://openalex.org/W1534355532","https://openalex.org/W1538023783","https://openalex.org/W1544439962","https://openalex.org/W1549353711","https://openalex.org/W1564534945","https://openalex.org/W1576818901","https://openalex.org/W1583833196","https://openalex.org/W1590984588","https://openalex.org/W1600795850","https://openalex.org/W1641379095","https://openalex.org/W1646752922","https://openalex.org/W1689445748","https://openalex.org/W1705501381","https://openalex.org/W1889531669","https://openalex.org/W1914583973","https://openalex.org/W1916228951","https://openalex.org/W1963754118","https://openalex.org/W1978181253","https://openalex.org/W1987187457","https://openalex.org/W1993587028","https://openalex.org/W1993740947","https://openalex.org/W2003323955","https://openalex.org/W2009533501","https://openalex.org/W2009767855","https://openalex.org/W2012391952","https://openalex.org/W2016648380","https://openalex.org/W2027945080","https://openalex.org/W2044676734","https://openalex.org/W2049287437","https://openalex.org/W2050417267","https://openalex.org/W2055178087","https://openalex.org/W2062122188","https://openalex.org/W2067619284","https://openalex.org/W2071311198","https://openalex.org/W2072164538","https://openalex.org/W2076337359","https://openalex.org/W2078226168","https://openalex.org/W2085130511","https://openalex.org/W2097571405","https://openalex.org/W2100370041","https://openalex.org/W2100677568","https://openalex.org/W2101915445","https://openalex.org/W2102734279","https://openalex.org/W2106451198","https://openalex.org/W2107726111","https://openalex.org/W2109330238","https://openalex.org/W2113204985","https://openalex.org/W2113501460","https://openalex.org/W2113998737","https://openalex.org/W2116339921","https://openalex.org/W2117341272","https://openalex.org/W2119053738","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2124868070","https://openalex.org/W2125801896","https://openalex.org/W2126297944","https://openalex.org/W2128643385","https://openalex.org/W2141650360","https://openalex.org/W2143680741","https://openalex.org/W2149054115","https://openalex.org/W2149162789","https://openalex.org/W2151676833","https://openalex.org/W2152610444","https://openalex.org/W2162813238","https://openalex.org/W2164568552","https://openalex.org/W2166843422","https://openalex.org/W2169022337","https://openalex.org/W2312609093","https://openalex.org/W2378066718","https://openalex.org/W2412433624","https://openalex.org/W3139377883","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W2141650360","https://openalex.org/W2072164538","https://openalex.org/W2143680741","https://openalex.org/W2136617285","https://openalex.org/W7097037065","https://openalex.org/W2043806097","https://openalex.org/W7221520672","https://openalex.org/W7100078473","https://openalex.org/W7099433457","https://openalex.org/W2201042428"],"abstract_inverted_index":{"Aggregation":[0],"of":[1,17,24,65,81,86,177,200,247,279,286,348],"multiple":[2,94,350],"Reinforcement":[3,100],"Learning":[4,101,227],"(RL)":[5],"algorithms":[6,50,67,82,187],"is":[7,55,73,104,181,222,252,291],"a":[8,25,92,115,136,236,349],"new":[9,93],"and":[10,83,118,134,145,206,288,304,326,337,344],"effective":[11],"technique":[12],"to":[13,41,77,122,166,193,293,297],"improve":[14,194,298,345],"the":[15,33,59,63,79,84,143,164,169,174,195,263,267,299,313,334,341],"quality":[16,23],"Sequential":[18],"Decision":[19],"Making":[20],"(SDM).":[21],"The":[22,127,150,239,250,271],"SDM":[26,44,310],"depends":[27],"on":[28,224,254,308],"long-term":[29],"rewards":[30],"rather":[31],"than":[32,58],"instant":[34],"rewards.":[35],"RL":[36,49,66,95,109,219,242,275,351],"methods":[37,244],"are":[38,153,210,245,277,306],"often":[39],"adopted":[40],"deal":[42,158],"with":[43,159,218],"problems.":[45],"\\n":[46,208,302],"\\nAlthough":[47],"many":[48],"have":[51],"been":[52],"developed,":[53],"none":[54],"consistently":[56],"better":[57],"others.":[60],"In":[61,106],"addition,":[62],"parameters":[64],"significantly":[68],"influence":[69],"learning":[70,116,161,171,178,186,196,214,284,300,342,346],"performances.":[71],"There":[72],"no":[74],"universal":[75],"rule":[76],"guide":[78],"choice":[80],"setting":[85],"parameters.":[87,179],"To":[88],"handle":[89],"this":[90,248,280],"difficulty,":[91],"system":[96],"-":[97],"Aggregated":[98],"Multiple":[99],"System":[102],"(AMRLS)":[103],"developed.":[105],"AMRLS,":[107],"each":[108],"algorithm":[110,172],"(learner)":[111],"learns":[112,230],"individually":[113],"in":[114,191,198,266],"module":[117,129],"provides":[119,135],"its":[120],"output":[121],"an":[123,215,231],"intelligent":[124],"aggregation":[125,128],"module.":[126],"dynamically":[130],"aggregates":[131],"these":[132],"outputs":[133],"final":[137],"decision.":[138],"Then,":[139],"all":[140],"learners":[141],"take":[142],"action":[144],"update":[146],"their":[147],"policies":[148],"individually.":[149],"two":[151,211],"processes":[152],"performed":[154],"alternatively.":[155],"AMRLS":[156,192],"can":[157,188,339],"dynamic":[160],"problems":[162],"without":[163],"need":[165],"search":[167],"for":[168,213,262],"optimal":[170,175,216,232,264],"or":[173],"values":[176],"It":[180],"claimed":[182],"that":[183,333],"several":[184,309],"complementary":[185],"be":[189],"integrated":[190],"performance":[197,347],"terms":[199],"success":[201],"rate,":[202],"robustness,":[203],"confidence,":[204],"redundance,":[205],"complementariness.":[207],"\\nThere":[209],"strategies":[212],"policy":[217,233,265,269],"methods.":[220],"One":[221],"based":[223,253],"Value":[225],"Function":[226],"(VFL),":[228],"which":[229,259],"expressed":[234],"as":[235],"value":[237],"function.":[238],"Temporal":[240],"Difference":[241],"(TDRL)":[243],"examples":[246],"strategy.":[249,281],"other":[251],"Direct":[255],"Policy":[256],"Search":[257],"(DPS),":[258],"directly":[260],"searches":[261],"potential":[268],"space.":[270],"Genetic":[272],"Algorithms":[273],"(GAs)-based":[274],"(GARL)":[276],"instances":[278],"A":[282],"hybrid":[283],"architecture":[285],"GARL":[287],"TDRL,":[289],"HGATDRL,":[290],"proposed":[292,335],"combine":[294],"them":[295],"together":[296],"ability.":[301],"\\nAMRLS":[303],"HGATDRL":[305],"tested":[307],"problems,":[311],"including":[312],"maze":[314],"world":[315],"problem,":[316,319,325],"pursuit":[317],"domain":[318],"cart-pole":[320],"balancing":[321],"system,":[322],"mountain":[323],"car":[324],"flight":[327],"control":[328],"system.":[329,352],"Experimental":[330],"results":[331],"show":[332],"framework":[336],"method":[338],"enhance":[340],"ability":[343]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}