{"id":"https://openalex.org/W2995197494","doi":"https://doi.org/10.1109/wcsp.2019.8928124","title":"Selector-Actor-Critic and Tuner-Actor-Critic Algorithms for Reinforcement Learning","display_name":"Selector-Actor-Critic and Tuner-Actor-Critic Algorithms for Reinforcement Learning","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2995197494","doi":"https://doi.org/10.1109/wcsp.2019.8928124","mag":"2995197494"},"language":"en","primary_location":{"id":"doi:10.1109/wcsp.2019.8928124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcsp.2019.8928124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Wireless Communications and Signal Processing (WCSP)","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/A5038958766","display_name":"Ala\u2019eddin Masadeh","orcid":"https://orcid.org/0000-0001-8754-6898"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ala'eddin Masadeh","raw_affiliation_strings":["Iowa State University (ISU), Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University (ISU), Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009345756","display_name":"Zhengdao Wang","orcid":"https://orcid.org/0000-0003-2491-7879"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengdao Wang","raw_affiliation_strings":["Iowa State University (ISU), Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University (ISU), Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069714415","display_name":"Ahmed E. Kamal","orcid":"https://orcid.org/0000-0002-6631-3478"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed E. Kamal","raw_affiliation_strings":["Iowa State University (ISU), Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University (ISU), Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038958766"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.2886,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68296982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937999844551086,"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":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.849833607673645},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8406343460083008},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790770292282104},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6051598191261292},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.585678219795227},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4987523555755615},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4909410774707794},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47542718052864075},{"id":"https://openalex.org/keywords/current","display_name":"Current (fluid)","score":0.4315224289894104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40215983986854553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23495134711265564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19282549619674683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15532681345939636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13770142197608948},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06542155146598816}],"concepts":[{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.849833607673645},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8406343460083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790770292282104},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6051598191261292},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.585678219795227},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4987523555755615},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4909410774707794},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47542718052864075},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.4315224289894104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40215983986854553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23495134711265564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19282549619674683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15532681345939636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13770142197608948},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06542155146598816},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wcsp.2019.8928124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcsp.2019.8928124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Wireless Communications and Signal Processing (WCSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:lib.dr.iastate.edu:ece_conf-1105","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/ece_conf/104","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Conference Papers, Posters and Presentations","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1491843047","https://openalex.org/W1830171635","https://openalex.org/W1966086707","https://openalex.org/W2012587148","https://openalex.org/W2094387729","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2154208977","https://openalex.org/W2165303028","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2520760276","https://openalex.org/W2586823359","https://openalex.org/W2625967765","https://openalex.org/W2766447205","https://openalex.org/W2887776796","https://openalex.org/W2950471160","https://openalex.org/W2953334758","https://openalex.org/W2962872206","https://openalex.org/W2963424548","https://openalex.org/W2963864421","https://openalex.org/W4205513846","https://openalex.org/W4214717370","https://openalex.org/W4234430590","https://openalex.org/W6600556750","https://openalex.org/W6696324988","https://openalex.org/W6753870703"],"related_works":["https://openalex.org/W2154107929","https://openalex.org/W4290057712","https://openalex.org/W2168846948","https://openalex.org/W2559413996","https://openalex.org/W2559844932","https://openalex.org/W2185884583","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"two":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"architectures,":[7],"which":[8],"mimic":[9],"rational":[10],"humans":[11],"in":[12],"the":[13,17,38,58,63,68,73,77,97,101,106,109,113,115,118,123,126,137,141,145,148,158,161],"way":[14],"of":[15,57,85,100,125,147,160],"analyzing":[16],"available":[18],"information":[19],"and":[20,30,52,83,92,108,151],"making":[21],"decisions.":[22],"The":[23,55],"proposed":[24,149,162],"algorithms":[25,163],"are":[26,34],"called":[27],"selector-actor-critic":[28],"(SAC)":[29],"tuner-actor-critic":[31],"(TAC).":[32],"They":[33],"obtained":[35],"by":[36,136],"modifying":[37],"well":[39],"known":[40],"actor-critic":[41],"(AC)":[42],"algorithm.":[43],"SAC":[44],"is":[45,60,80,134],"equipped":[46],"with":[47,153],"an":[48,90],"actor,":[49,91],"a":[50,53,86,88,93],"critic,":[51],"selector.":[54],"role":[56],"selector":[59],"to":[61,121,139,156],"determine":[62],"most":[64],"promising":[65],"action":[66],"at":[67],"current":[69,102,127],"state":[70],"based":[71],"on":[72],"last":[74],"estimate":[75],"from":[76,105,112],"critic.":[78,94],"TAC":[79],"model":[81,111],"based,":[82],"consists":[84],"tuner,":[87],"model-learner,":[89,114],"After":[95],"receiving":[96],"approximated":[98],"value":[99,124,133],"state-action":[103,128],"pair":[104],"critic":[107],"learned":[110],"tuner":[116],"uses":[117],"Bellman":[119],"equation":[120],"tune":[122],"pair.":[129],"Then,":[130],"this":[131],"tuned":[132],"used":[135],"actor":[138],"optimize":[140],"policy.":[142],"We":[143],"investigate":[144],"performance":[146],"algorithms,":[150],"compare":[152],"AC":[154],"algorithm":[155],"show":[157],"advantages":[159],"using":[164],"numerical":[165],"simulations.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}