{"id":"https://openalex.org/W2126267541","doi":"https://doi.org/10.1109/ijcnn.2004.1380882","title":"Learning with binary-valued utility using derivative adaptive critic methods","display_name":"Learning with binary-valued utility using derivative adaptive critic methods","publication_year":2005,"publication_date":"2005-01-31","ids":{"openalex":"https://openalex.org/W2126267541","doi":"https://doi.org/10.1109/ijcnn.2004.1380882","mag":"2126267541"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","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/A5046976303","display_name":"Shari Matzner","orcid":null},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S.A. Matzner","raw_affiliation_strings":["NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044905313","display_name":"T.T. Shannon","orcid":"https://orcid.org/0000-0002-1095-4110"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.T. Shannon","raw_affiliation_strings":["NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081813106","display_name":"George G. Lendaris","orcid":null},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.G. Lendaris","raw_affiliation_strings":["NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"NW Computational Intelligence Laboratory, Portland State University, Portland, OR, USA","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046976303"],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":null,"apc_paid":null,"fwci":0.3366,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64230179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1805","last_page":"1810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9934999942779541,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9391000270843506,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7672734260559082},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6614017486572266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.607903242111206},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.592190146446228},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5690211653709412},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.5521183013916016},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5335638523101807},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46219804883003235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543546438217163},{"id":"https://openalex.org/keywords/quadratic-programming","display_name":"Quadratic programming","score":0.4215206503868103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2221851646900177}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7672734260559082},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6614017486572266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607903242111206},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.592190146446228},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5690211653709412},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.5521183013916016},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5335638523101807},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46219804883003235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543546438217163},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.4215206503868103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2221851646900177},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"},{"id":"pmh:oai:pdxscholar.library.pdx.edu:sysc_fac-1230","is_oa":false,"landing_page_url":"https://pdxscholar.library.pdx.edu/sysc_fac/217","pdf_url":null,"source":{"id":"https://openalex.org/S4377196300","display_name":"PDXScholar  (Portland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126345244","host_organization_name":"Portland State University","host_organization_lineage":["https://openalex.org/I126345244"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Systems Science Faculty Publications and Presentations","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W2062533874","https://openalex.org/W2091565802","https://openalex.org/W2102953482","https://openalex.org/W2128562176","https://openalex.org/W2136064843","https://openalex.org/W2149046201","https://openalex.org/W3213472335","https://openalex.org/W4298300677","https://openalex.org/W6603762378","https://openalex.org/W6681672637","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2961374456","https://openalex.org/W4321438667"],"abstract_inverted_index":{"Adaptive":[0],"critic":[1,37,73],"methods":[2,74],"for":[3,22,75,117],"reinforcement":[4,30,54,70],"learning":[5,24,118],"are":[6,17],"known":[7],"to":[8,12,126],"provide":[9],"consistent":[10],"solutions":[11],"optimal":[13,121],"control":[14],"problems,":[15],"and":[16,47,98],"also":[18],"considered":[19],"plausible":[20],"models":[21],"cognitive":[23],"processes.":[25],"This":[26],"work":[27],"discusses":[28],"binary":[29,69],"in":[31],"the":[32,57,76,91,106,112],"context":[33],"of":[34,60,86],"three":[35],"adaptive":[36,72],"methods:":[38],"heuristic":[39,44,50],"dynamic":[40],"programming":[41,45,51],"(HDP),":[42],"dual":[43,49],"(DHP),":[46],"globalized":[48],"(GDHP).":[52],"Binary":[53],"arises":[55],"when":[56],"qualitative":[58],"measure":[59],"success":[61],"is":[62,109,115],"simply":[63],"\"pass\"":[64],"or":[65],"\"fail\".":[66],"We":[67],"implement":[68],"with":[71,95,123],"pole-cart":[77],"benchmark":[78],"problem.":[79],"Results":[80],"demonstrate":[81],"two":[82],"qualitatively":[83],"dissimilar":[84],"classes":[85],"controllers:":[87],"those":[88,99,127],"that":[89,100,111,131],"replicate":[90],"system":[92],"stabilization":[93],"achieved":[94],"quadratic":[96,136],"utility,":[97],"merely":[101],"succeed":[102],"at":[103],"not":[104],"dropping":[105],"pole.":[107],"It":[108],"found":[110],"GDHP":[113],"method":[114],"effective":[116],"an":[119],"approximately":[120],"solution,":[122],"results":[124],"comparable":[125],"obtained":[128],"via":[129],"DHP":[130],"uses":[132],"a":[133],"more":[134],"informative,":[135],"utility":[137],"function.":[138]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}