{"id":"https://openalex.org/W2051269406","doi":"https://doi.org/10.1177/105971239500400102","title":"Reinforcement Learning Applied to a Differential Game","display_name":"Reinforcement Learning Applied to a Differential Game","publication_year":1995,"publication_date":"1995-09-01","ids":{"openalex":"https://openalex.org/W2051269406","doi":"https://doi.org/10.1177/105971239500400102","mag":"2051269406"},"language":"en","primary_location":{"id":"doi:10.1177/105971239500400102","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239500400102","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/A5103551222","display_name":"Mance E. Harmon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mance E. Harmon","raw_affiliation_strings":["Wright Laboratory","WRIGHT LABORATORY"],"affiliations":[{"raw_affiliation_string":"Wright Laboratory","institution_ids":[]},{"raw_affiliation_string":"WRIGHT LABORATORY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109861252","display_name":"Leemon C. Baird","orcid":null},"institutions":[{"id":"https://openalex.org/I430641","display_name":"United States Air Force Academy","ror":"https://ror.org/0055d0g64","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I4210089612","https://openalex.org/I4210102105","https://openalex.org/I430641"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leemon C. Baird","raw_affiliation_strings":["United States Air Force Academy","United states Air Force Academy"],"affiliations":[{"raw_affiliation_string":"United States Air Force Academy","institution_ids":["https://openalex.org/I430641"]},{"raw_affiliation_string":"United states Air Force Academy","institution_ids":["https://openalex.org/I430641"]}]},{"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":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103551222"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5626,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.82244775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"1","first_page":"3","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9954000115394592,"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":0.9954000115394592,"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/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8524236679077148},{"id":"https://openalex.org/keywords/missile","display_name":"Missile","score":0.7231609225273132},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.61192786693573},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.5980479121208191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5449449419975281},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5266815423965454},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.49779367446899414},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4869168996810913},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.46969959139823914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002176821231842},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36765244603157043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30448561906814575},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21926763653755188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07793542742729187}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8524236679077148},{"id":"https://openalex.org/C2778857364","wikidata":"https://www.wikidata.org/wiki/Q974850","display_name":"Missile","level":2,"score":0.7231609225273132},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.61192786693573},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.5980479121208191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5449449419975281},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5266815423965454},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.49779367446899414},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4869168996810913},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.46969959139823914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002176821231842},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36765244603157043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30448561906814575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21926763653755188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07793542742729187},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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:10.1177/105971239500400102","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239500400102","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1512944870","https://openalex.org/W1543217731","https://openalex.org/W1545148916","https://openalex.org/W1557517019","https://openalex.org/W1563489070","https://openalex.org/W1621423688","https://openalex.org/W1646707810","https://openalex.org/W1976564839","https://openalex.org/W2037584050","https://openalex.org/W2103626435","https://openalex.org/W2107649750","https://openalex.org/W2119717200","https://openalex.org/W2121832485","https://openalex.org/W2143867281","https://openalex.org/W2888914392","https://openalex.org/W3011120880","https://openalex.org/W3145013517","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2937181779","https://openalex.org/W2146763310","https://openalex.org/W4382935469","https://openalex.org/W3167472281","https://openalex.org/W1968481698","https://openalex.org/W2182304831","https://openalex.org/W1556532828","https://openalex.org/W1511927616","https://openalex.org/W1574991376","https://openalex.org/W2051269406"],"abstract_inverted_index":{"An":[0],"application":[1],"of":[2,24,50,142,149,175],"reinforcement":[3,13,81,100,132],"learning":[4,14,82,101,133],"to":[5,89,111,124,136,172,183],"a":[6,17,30,43,53,56,70,95],"linear-quadratic,":[7],"differential":[8,109],"game":[9,28,48],"is":[10,29,86,106,170,181],"presented.":[11],"The":[12,27,47,99,140],"system":[15,134],"uses":[16],"recently":[18],"developed":[19],"algorithm,":[20],"the":[21,58,61,64,67,76,80,113,118,125,130,137,144,176,186],"residual-gradient":[22,145],"form":[23],"advantage":[25,150,158],"updating.":[26],"Markov":[31],"decision":[32],"process":[33],"with":[34],"continuous":[35],"time,":[36],"states,":[37],"and":[38,42,55,63,72,146,152],"actions,":[39],"linear":[40],"dynamics,":[41],"quadratic":[44],"cost":[45],"function.":[46],"consists":[49],"two":[51],"players,":[52],"missile":[54,59,71],"plane;":[57],"pursues":[60],"plane":[62,65,73],"evades":[66],"missile.":[68],"Although":[69],"scenario":[74],"was":[75],"chosen":[77],"test":[78],"bed,":[79],"approach":[83],"presented":[84],"here":[85],"equally":[87],"applicable":[88],"biologically":[90],"based":[91],"systems,":[92],"such":[93],"as":[94,185],"predator":[96],"pursuing":[97],"prey.":[98],"algorithm":[102],"for":[103,108],"optimal":[104,138],"control":[105],"modified":[107],"games":[110],"find":[112],"minimax":[114],"point":[115],"rather":[116],"than":[117,162],"maximum.":[119],"Simulation":[120],"results":[121],"are":[122,154],"compared":[123],"analytical":[126],"solution,":[127],"demonstrating":[128,156],"that":[129,157],"simulated":[131],"converges":[135,160],"answer.":[139],"performance":[141],"both":[143],"non-residual-gradient":[147],"forms":[148],"updating":[151,159,168],"Q-learning":[153,163,180],"compared,":[155],"faster":[161],"in":[164],"all":[165],"simulations.":[166],"Advantage":[167],"also":[169],"demonstrated":[171],"converge":[173,184],"regardless":[174],"time":[177,187],"step":[178,188],"duration;":[179],"unable":[182],"duration":[189],"grows":[190],"small.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}