{"id":"https://openalex.org/W2038880985","doi":"https://doi.org/10.1109/smc.2014.6974146","title":"Multiple-model Q-learning for stochastic reinforcement delays","display_name":"Multiple-model Q-learning for stochastic reinforcement delays","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2038880985","doi":"https://doi.org/10.1109/smc.2014.6974146","mag":"2038880985"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2014.6974146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2014.6974146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5084154287","display_name":"J. S. Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Campbell","raw_affiliation_strings":["Systems and Computer Engineering, Carleton University, Ottawa, Ontario, Canada","Systems and Computer Engineering Carleton University Ottawa Ontario Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems and Computer Engineering, Carleton University, Ottawa, Ontario, Canada","institution_ids":["https://openalex.org/I67031392"]},{"raw_affiliation_string":"Systems and Computer Engineering Carleton University Ottawa Ontario Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025867957","display_name":"Sidney Givigi","orcid":"https://orcid.org/0000-0002-3829-3545"},"institutions":[{"id":"https://openalex.org/I51768193","display_name":"Royal Military College of Canada","ror":"https://ror.org/04yr71909","country_code":"CA","type":"education","lineage":["https://openalex.org/I51768193"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sidney N. Givigi","raw_affiliation_strings":["Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada","Electrical and Computer Engineering, Royal Military College of Canada Kingston, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada","institution_ids":["https://openalex.org/I51768193"]},{"raw_affiliation_string":"Electrical and Computer Engineering, Royal Military College of Canada Kingston, Ontario, Canada","institution_ids":["https://openalex.org/I51768193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018347314","display_name":"Howard M. Schwartz","orcid":"https://orcid.org/0000-0002-4489-5892"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Howard M. Schwartz","raw_affiliation_strings":["Systems and Computer Engineering, Carleton University, Ottawa, Ontario, Canada","Systems and Computer Engineering Carleton University Ottawa Ontario Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems and Computer Engineering, Carleton University, Ottawa, Ontario, Canada","institution_ids":["https://openalex.org/I67031392"]},{"raw_affiliation_string":"Systems and Computer Engineering Carleton University Ottawa Ontario Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6203,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.67212353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1611","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":0.9983000159263611,"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":0.9983000159263611,"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":0.996399998664856,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9958999752998352,"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":0.9499666094779968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7424255013465881},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6261810660362244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6097070574760437},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5643322467803955},{"id":"https://openalex.org/keywords/craft","display_name":"Craft","score":0.48759856820106506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065389037132263},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3339933156967163},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3305813670158386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1607424020767212},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10307025909423828}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9499666094779968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7424255013465881},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6261810660362244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6097070574760437},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5643322467803955},{"id":"https://openalex.org/C2779732396","wikidata":"https://www.wikidata.org/wiki/Q2207288","display_name":"Craft","level":2,"score":0.48759856820106506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065389037132263},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3339933156967163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3305813670158386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1607424020767212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10307025909423828},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2014.6974146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2014.6974146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":18,"referenced_works":["https://openalex.org/W1532887414","https://openalex.org/W1538318259","https://openalex.org/W1591808955","https://openalex.org/W1977467218","https://openalex.org/W2051829768","https://openalex.org/W2066477246","https://openalex.org/W2097951814","https://openalex.org/W2105917283","https://openalex.org/W2107726111","https://openalex.org/W2117864026","https://openalex.org/W2121863487","https://openalex.org/W2147750403","https://openalex.org/W2158829052","https://openalex.org/W4205513846","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W6667180500","https://openalex.org/W6676007687"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"The":[0,47,75],"main":[1],"contribution":[2],"of":[3,31,59,101],"this":[4],"work":[5],"is":[6,21,78,83,95],"a":[7,16,39,86,102],"novel":[8,48],"machine":[9],"reinforcement":[10,26,33],"learning":[11,103],"algorithm":[12,36,77],"for":[13,43],"problems":[14],"where":[15],"Poissonian":[17],"stochastic":[18],"time":[19,62],"delay":[20],"present":[22],"in":[23,61,72,105],"the":[24,29,32,35,44,73,92,99],"agent's":[25,45],"signal.":[27],"Despite":[28],"presence":[30],"noise,":[34],"can":[37,50],"craft":[38],"suitable":[40],"control":[41],"policy":[42],"environment.":[46],"approach":[49],"deal":[51],"with":[52,108],"reinforcements":[53],"which":[54,67],"may":[55,64],"be":[56],"received":[57],"out":[58],"order":[60],"or":[63],"even":[65],"overlap,":[66],"was":[68],"not":[69],"previously":[70],"considered":[71],"literature.":[74],"proposed":[76,93],"simulated":[79],"and":[80],"its":[81],"performance":[82,100],"compared":[84],"to":[85,97],"standard":[87],"Q-learning":[88],"algorithm.":[89],"Through":[90],"simulation,":[91],"method":[94],"found":[96],"improve":[98],"agent":[104],"an":[106],"environment":[107],"Poissonian-type":[109],"stochastically":[110],"delayed":[111],"rewards.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}