{"id":"https://openalex.org/W63529905","doi":null,"title":"Reinforcement learning : theory, methods and application to decision support systems","display_name":"Reinforcement learning : theory, methods and application to decision support systems","alternate_titles":[],"publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W63529905","mag":"63529905"},"language":"en","primary_location":{"id":"pmh:oai:scholar.sun.ac.za:10019.1/5304","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10019.1/5304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400300","display_name":"SUNScholar (Stellenbosch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I26092322","host_organization_name":"Stellenbosch University","host_organization_lineage":["https://openalex.org/I26092322"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"parent_works":[],"lineage":["https://openalex.org/W63529905"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5025662028","display_name":"Hildegarde Suzanne Mouton","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Hildegarde Suzanne Mouton","raw_affiliation_strings":["Stellenbosch : University of Stellenbosch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch : University of Stellenbosch","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025662028"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.9509999752044678},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8809999823570251},{"id":"https://openalex.org/keywords/decision-support-system","display_name":"decision support system","score":0.9079999923706055},{"id":"https://openalex.org/keywords/discount-factor","display_name":"discount factor","score":0.8080000281333923},{"id":"https://openalex.org/keywords/learning-rate","display_name":"learning rate","score":0.9819999933242798},{"id":"https://openalex.org/keywords/battlefield-decision-making","display_name":"battlefield decision-making","score":0.5199999809265137},{"id":"https://openalex.org/keywords/situational-awareness","display_name":"situational awareness","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6912466287612915},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5188918709754944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43471601605415344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36991214752197266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3353215456008911},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2823026180267334},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12399032711982727}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:scholar.sun.ac.za:10019.1/5304","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10019.1/5304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400300","display_name":"SUNScholar (Stellenbosch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I26092322","host_organization_name":"Stellenbosch University","host_organization_lineage":["https://openalex.org/I26092322"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"mag:63529905","doi":null,"is_oa":false,"landing_page_url":"https://scholar.sun.ac.za/handle/10019.1/5304?show=full","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W81226926","https://openalex.org/W205043379","https://openalex.org/W1484312206","https://openalex.org/W1492640216","https://openalex.org/W1515851193","https://openalex.org/W1585546214","https://openalex.org/W1601081659","https://openalex.org/W1704640478","https://openalex.org/W1969166509","https://openalex.org/W1992981726","https://openalex.org/W2028145673","https://openalex.org/W2038410048","https://openalex.org/W2065269360","https://openalex.org/W2110636839","https://openalex.org/W2113043717","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2125207095","https://openalex.org/W2131600418","https://openalex.org/W2164579613","https://openalex.org/W2165873990","https://openalex.org/W2168178000","https://openalex.org/W2341171179","https://openalex.org/W2405440615","https://openalex.org/W2914656440","https://openalex.org/W3023540311","https://openalex.org/W3183630977"],"related_works":["https://openalex.org/W2011284091","https://openalex.org/W4400061989","https://openalex.org/W2128786740","https://openalex.org/W2050024476","https://openalex.org/W2518713116","https://openalex.org/W2751379610","https://openalex.org/W4313202138","https://openalex.org/W2184117900","https://openalex.org/W2107222090"],"abstract_inverted_index":{"ENGLISH":[0],"ABSTRACT:":[1],"In":[2],"this":[3,218],"dissertation":[4],"we":[5,20,241],"study":[6],"the":[7,48,54,94,100,115,121,128,140,160,168,198,212,233,239],"machine":[8],"learning":[9,39,116],"subfield":[10],"of":[11,47,61,193,201,203,238],"Reinforcement":[12],"Learning":[13],"(RL).":[14],"After":[15],"developing":[16],"a":[17,22,44,58,106,185],"coherent":[18],"background,":[19],"apply":[21],"Monte":[23],"Carlo":[24],"(MC)":[25],"control":[26,40,56,149],"algorithm":[27,150],"with":[28,133,151,220],"exploring":[29,152],"starts":[30,153],"(MCES),":[31],"as":[32,34,79,81,97,179],"well":[33,80],"an":[35],"off-policy":[36,169],"Temporal-Difference":[37],"(TD)":[38],"algorithm,":[41,57,96,171],"Q-learning,":[42,172],"to":[43,74,93,102,135,159,235],"simplified":[45],"version":[46],"Weapon":[49],"Assignment":[50],"(WA)":[51],"problem.":[52,162],"For":[53],"MCES":[55],"discount":[59,88,122],"parameter":[60,89,123],"\u03c4":[62,144],"=":[63,111],"1":[64],"is":[65,176,184],"used.":[66],"This":[67],"gives":[68,154],"very":[69],"promising":[70,155],"results":[71,130,156],"when":[72,157],"applied":[73,92,158],"7":[75,77],"\u00d7":[76,83],"grids,":[78],"71":[82,84],"grids.":[85],"The":[86,147,181],"same":[87],"cannot":[90],"be":[91],"Q-learning":[95],"it":[98,175],"causes":[99],"Q-values":[101],"diverge.":[103],"We":[104],"take":[105],"greedy":[107],"approach,":[108],"setting":[109],"\u03b5":[110],"0,":[112],"and":[113,120,137,197,205,215,227],"vary":[114],"rate":[117],"(\u03b1":[118],")":[119],"(\u03c4).":[124],"Experimentation":[125],"shows":[126],"that":[127],"best":[129],"are":[131,207],"found":[132],"set":[134],"0.1":[136],"constrained":[138],"in":[139,217,223,244],"region":[141],"0.4":[142],"\u2264":[143,145],"0.7.":[146],"MC":[148],"WA":[161],"It":[163],"performs":[164],"significantly":[165],"better":[166],"than":[167],"TD":[170],"even":[173],"though":[174],"almost":[177],"twice":[178],"slow.":[180],"modern":[182,228],"battlefield":[183],"fast":[186],"paced,":[187],"information":[188],"rich":[189],"environment,":[190],"where":[191],"discovery":[192],"intent,":[194],"situation":[195],"awareness":[196],"rapid":[199],"evolution":[200],"concepts":[202],"operation":[204],"doctrine":[206],"critical":[208],"success":[209],"factors.":[210],"Combining":[211],"techniques":[213,222,230],"investigated":[214],"tested":[216],"work":[219],"other":[221],"Artificial":[224],"Intelligence":[225],"(AI)":[226],"computational":[229],"may":[231],"hold":[232],"key":[234],"solving":[236],"some":[237],"problems":[240],"now":[242],"face":[243],"warfare.":[245]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W63529905","counts_by_year":[],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2016-06-24T00:00:00"}
