{"id":"https://openalex.org/W2805646502","doi":"https://doi.org/10.1109/syscon.2018.8369536","title":"Applying expectation-maximization evaluation on approximate optimal control","display_name":"Applying expectation-maximization evaluation on approximate optimal control","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2805646502","doi":"https://doi.org/10.1109/syscon.2018.8369536","mag":"2805646502"},"language":"en","primary_location":{"id":"doi:10.1109/syscon.2018.8369536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/syscon.2018.8369536","pdf_url":null,"source":{"id":"https://openalex.org/S4306498283","display_name":"2018 Annual IEEE International Systems Conference (SysCon)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual IEEE International Systems Conference (SysCon)","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/A5065157136","display_name":"Songtao Zhang","orcid":"https://orcid.org/0000-0002-2463-4222"},"institutions":[{"id":"https://openalex.org/I106938459","display_name":"University of New Brunswick","ror":"https://ror.org/05nkf0n29","country_code":"CA","type":"education","lineage":["https://openalex.org/I106938459"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Songtao Zhang","raw_affiliation_strings":["Department of Mechanical Engineering, University of New Brunswick, Fredericton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of New Brunswick, Fredericton, Canada","institution_ids":["https://openalex.org/I106938459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048290919","display_name":"Rickey Dubay","orcid":"https://orcid.org/0000-0002-4132-6483"},"institutions":[{"id":"https://openalex.org/I106938459","display_name":"University of New Brunswick","ror":"https://ror.org/05nkf0n29","country_code":"CA","type":"education","lineage":["https://openalex.org/I106938459"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rickey Dubay","raw_affiliation_strings":["Department of Mechanical Engineering, University of New Brunswick, Fredericton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of New Brunswick, Fredericton, Canada","institution_ids":["https://openalex.org/I106938459"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065157136"],"corresponding_institution_ids":["https://openalex.org/I106938459"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05830389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9925000071525574,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9736999869346619,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6660970449447632},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.6626875400543213},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6395175457000732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6351408958435059},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5848925113677979},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5550450086593628},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5530661344528198},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5465883016586304},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5129424929618835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4961860775947571},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.48607710003852844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43592098355293274},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42328178882598877},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4228055477142334},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35515350103378296},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.29607534408569336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2371000051498413},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11759200692176819},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09833681583404541},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.06658998131752014}],"concepts":[{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6660970449447632},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.6626875400543213},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6395175457000732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351408958435059},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5848925113677979},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5550450086593628},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5530661344528198},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5465883016586304},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5129424929618835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4961860775947571},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.48607710003852844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43592098355293274},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42328178882598877},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4228055477142334},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35515350103378296},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29607534408569336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2371000051498413},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11759200692176819},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09833681583404541},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.06658998131752014},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/syscon.2018.8369536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/syscon.2018.8369536","pdf_url":null,"source":{"id":"https://openalex.org/S4306498283","display_name":"2018 Annual IEEE International Systems Conference (SysCon)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual IEEE International Systems Conference (SysCon)","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":12,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W560518094","https://openalex.org/W1573503290","https://openalex.org/W2011866373","https://openalex.org/W2013895638","https://openalex.org/W2101188133","https://openalex.org/W2165726932","https://openalex.org/W2484646121","https://openalex.org/W2993880730","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4253354958"],"related_works":["https://openalex.org/W2761624296","https://openalex.org/W4386994694","https://openalex.org/W4388738109","https://openalex.org/W2362901947","https://openalex.org/W2362086884","https://openalex.org/W1606071314","https://openalex.org/W2350210972","https://openalex.org/W1976188970","https://openalex.org/W2889559465","https://openalex.org/W2990541822"],"abstract_inverted_index":{"In":[0],"this":[1,137],"paper":[2],"we":[3,30,46],"proposed":[4],"an":[5,126],"approach":[6,138],"of":[7,18,34,39,50,57,76,106,125,136,147],"approximating":[8],"optimal":[9,127,159],"tracking":[10,43,70,81,160],"via":[11,122],"expectation-maximization":[12],"(EM)":[13],"evaluation.":[14],"From":[15],"the":[16,32,48,52,61,64,69,74,78,90,95,104,107,116,119,145,148,153,158],"discussion":[17],"applying":[19],"reinforcement":[20],"learning":[21,86,89,94],"(RL)":[22],"for":[23,63,68],"a":[24,36,42,130,140],"system":[25,65,143],"with":[26,152],"unknown":[27],"internal":[28],"dynamics,":[29],"present":[31],"challenge":[33],"using":[35,139],"classical":[37],"frame":[38,109,150],"Q-learning":[40,58,108,149],"on":[41,103],"task.":[44,71,161],"Further":[45],"explained":[47,73],"idea":[49],"redefining":[51],"cost":[53],"function":[54],"(i.e.":[55,88],"criterion)":[56],"to":[59,118,157],"satisfy":[60],"requirement":[62],"dynamic":[66],"knowledge":[67],"We":[72],"advantages":[75],"dividing":[77],"original":[79],"trajectory":[80],"task":[82],"into":[83],"two":[84],"machine":[85],"subtasks":[87],"quadratic":[91],"regulator":[92,128],"and":[93,110,129],"baseline":[96,131],"command":[97],"generator)":[98],"on-line.":[99],"Details":[100],"are":[101],"given":[102],"integration":[105],"EM":[111,154],"algorithm":[112,155],"as":[113,115],"well":[114],"convergence":[117],"optimum":[120],"control":[121],"iterative":[123],"estimation":[124],"generator.":[132],"Initial":[133],"simulation":[134],"results":[135],"second":[141],"order":[142],"showed":[144],"ability":[146],"integrated":[151],"approximates":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}