{"id":"https://openalex.org/W2037584050","doi":"https://doi.org/10.1177/105971239300100303","title":"A Hierarchical Network of Provably Optimal Learning Control Systems: Extensions of the Associative Control Process (ACP) Network","display_name":"A Hierarchical Network of Provably Optimal Learning Control Systems: Extensions of the Associative Control Process (ACP) Network","publication_year":1993,"publication_date":"1993-01-01","ids":{"openalex":"https://openalex.org/W2037584050","doi":"https://doi.org/10.1177/105971239300100303","mag":"2037584050"},"language":"en","primary_location":{"id":"doi:10.1177/105971239300100303","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239300100303","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-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/A5109861252","display_name":"Leemon C. Baird","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Leemon C. Baird","raw_affiliation_strings":["Wright Laboratory","WRIGHT LABORATORY"],"affiliations":[{"raw_affiliation_string":"Wright Laboratory","institution_ids":[]},{"raw_affiliation_string":"WRIGHT LABORATORY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038077029","display_name":"A. Harry Klopf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Harry Klopf","raw_affiliation_strings":["Wright Laboratory","WRIGHT LABORATORY"],"affiliations":[{"raw_affiliation_string":"Wright Laboratory","institution_ids":[]},{"raw_affiliation_string":"WRIGHT LABORATORY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109861252"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7886,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90430229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":"3","first_page":"321","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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":0.9940999746322632,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9912999868392944,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8212597966194153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274240255355835},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5962318181991577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508427083492279},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4968741238117218},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4884154200553894},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45315927267074585},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4232312738895416},{"id":"https://openalex.org/keywords/hierarchical-control-system","display_name":"Hierarchical control system","score":0.42040136456489563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38008058071136475},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3518543839454651}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8212597966194153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274240255355835},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5962318181991577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508427083492279},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4968741238117218},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4884154200553894},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45315927267074585},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4232312738895416},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.42040136456489563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38008058071136475},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3518543839454651},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/105971239300100303","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239300100303","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W46130386","https://openalex.org/W50296447","https://openalex.org/W59055888","https://openalex.org/W119682760","https://openalex.org/W1491843047","https://openalex.org/W1500245617","https://openalex.org/W1538558539","https://openalex.org/W1557517019","https://openalex.org/W1563489070","https://openalex.org/W1599610710","https://openalex.org/W1610678877","https://openalex.org/W1628475528","https://openalex.org/W1907796993","https://openalex.org/W1976564839","https://openalex.org/W2012036715","https://openalex.org/W2012187514","https://openalex.org/W2040598998","https://openalex.org/W2052117683","https://openalex.org/W2064018461","https://openalex.org/W2074935255","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2096459303","https://openalex.org/W2097856935","https://openalex.org/W2100677568","https://openalex.org/W2101761545","https://openalex.org/W2103626435","https://openalex.org/W2107649750","https://openalex.org/W2113077545","https://openalex.org/W2131952509","https://openalex.org/W2133924084","https://openalex.org/W2141559645","https://openalex.org/W2151742051","https://openalex.org/W2158091072","https://openalex.org/W2161608691","https://openalex.org/W2317700292","https://openalex.org/W2540877599","https://openalex.org/W2914112863","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3145013517","https://openalex.org/W3198350258","https://openalex.org/W4253365321","https://openalex.org/W4298215580","https://openalex.org/W4299736415"],"related_works":["https://openalex.org/W2976657239","https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"An":[0],"associative":[1],"control":[2,9,226],"process":[3],"(ACP)":[4],"network":[5,126,177,206,250],"is":[6,67,82,231],"a":[7,14,70,175,200,218,221],"learning":[8,18,72,88,103,140,165,169,183,194,258],"system":[10,73],"that":[11,41,90,99,129,160],"can":[12,196],"reproduce":[13,100],"variety":[15],"of":[16,38,84,120,153,211,242],"animal":[17,87,102,139,164],"results":[19,89,104,166],"from":[20],"classical":[21],"and":[22,47,52,105,237,255],"instrumental":[23],"conditioning":[24],"experiments":[25],"(Klopf,":[26],"Morgan,":[27,51],"&":[28],"Weaver,":[29],"1993;":[30],"see":[31],"also":[32,173],"the":[33,86,101,112,117,124,138,145,150,163,204,212,247,252,261],"article,":[34],"'A":[35],"Hierarchical":[36],"Network":[37],"Control":[39],"Systems":[40],"Learn\").":[42],"The":[43,109,142,228],"ACP":[44,91,114,125,147,189,214,249],"networks":[45,92,215],"proposed":[46],"tested":[48],"by":[49,208],"Klopf,":[50],"Weaver":[53],"are":[54,106],"not":[55],"guaranteed,":[56],"however,":[57],"to":[58,123,127,156,158,216,233],"learn":[59,234],"optimal":[60,130,170],"policies":[61,131],"for":[62,69,220,260],"maximizing":[63],"reinforcement.":[64],"Optimal":[65],"behavior":[66],"guaranteed":[68],"reinforcement":[71,182],"such":[74],"as":[75],"Q-learning":[76,81,157,186],"(Watkins,":[77],"1989),":[78],"but":[79],"simple":[80],"incapable":[83],"reproducing":[85,137],"reproduce.":[93],"We":[94,172,202],"propose":[95,174],"two":[96],"new":[97],"models":[98],"provably":[107],"optimal.":[108],"first":[110],"model,":[111,144],"modified":[113],"network,":[115,148],"embodies":[116,149],"smallest":[118,151],"number":[119,152],"changes":[121,154],"necessary":[122,155],"guarantee":[128,159],"will":[132],"be":[133,197],"learned":[134],"while":[135,167],"still":[136,168],"results.":[141],"second":[143],"single-layer":[146,188,213,248],"it":[161],"reproduces":[162],"policies.":[171],"hierarchical":[176,205,229],"architecture":[178,207],"within":[179],"which":[180],"several":[181],"systems":[184],"(e.g.,":[185],"systems,":[187],"networks,":[190],"or":[191,251],"any":[192],"other":[193],"controller)":[195],"combined":[198],"in":[199],"hierarchy.":[201],"implement":[203],"combining":[209],"four":[210],"form":[217],"controller":[219,230,259],"standard":[222],"inverted":[223],"pendulum":[224],"dynamic":[225],"problem.":[227,263],"shown":[232],"more":[235,238],"reliably":[236],"than":[239,245],"an":[240],"order":[241],"magnitude":[243],"faster":[244],"either":[246],"Barto,":[253],"Sutton,":[254],"Anderson":[256],"(1983)":[257],"benchmark":[262]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}