{"id":"https://openalex.org/W1979685636","doi":"https://doi.org/10.1109/cig.2009.5286497","title":"Improving Temporal Difference game agent control using a dynamic exploration during control learning","display_name":"Improving Temporal Difference game agent control using a dynamic exploration during control learning","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W1979685636","doi":"https://doi.org/10.1109/cig.2009.5286497","mag":"1979685636"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2009.5286497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2009.5286497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Computational Intelligence and Games","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/A5017163549","display_name":"Leo Galway","orcid":"https://orcid.org/0000-0002-1881-1501"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leo Galway","raw_affiliation_strings":["School of Computing and Information Engineering, University of Ulster, UK","School of Computing and Information Engineering at the University of Ulster, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Engineering, University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing and Information Engineering at the University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053724421","display_name":"Darryl Charles","orcid":"https://orcid.org/0000-0002-8546-6066"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Darryl Charles","raw_affiliation_strings":["School of Computing and Information Engineering, University of Ulster, UK","School of Computing and Information Engineering at the University of Ulster, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Engineering, University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing and Information Engineering at the University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077309331","display_name":"Michaela Black","orcid":"https://orcid.org/0000-0002-5140-2566"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michaela Black","raw_affiliation_strings":["School of Computing and Information Engineering, University of Ulster, UK","School of Computing and Information Engineering at the University of Ulster, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Engineering, University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing and Information Engineering at the University of Ulster, UK","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.453,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72030058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9898999929428101,"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":0.7773734331130981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.734539806842804},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.6316275596618652},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4423179626464844},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42778024077415466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40104690194129944},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.28105628490448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07467180490493774}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7773734331130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734539806842804},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.6316275596618652},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4423179626464844},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42778024077415466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40104690194129944},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.28105628490448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07467180490493774},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2009.5286497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2009.5286497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Computational Intelligence and Games","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41346994","https://openalex.org/W47897054","https://openalex.org/W70710081","https://openalex.org/W73587361","https://openalex.org/W115079321","https://openalex.org/W161065179","https://openalex.org/W165717528","https://openalex.org/W170196830","https://openalex.org/W1515851193","https://openalex.org/W1556370853","https://openalex.org/W1576818901","https://openalex.org/W1580563784","https://openalex.org/W1582046617","https://openalex.org/W1779246287","https://openalex.org/W2045846579","https://openalex.org/W2108012394","https://openalex.org/W2109801420","https://openalex.org/W2120321549","https://openalex.org/W2124548463","https://openalex.org/W2234132233","https://openalex.org/W2613052675","https://openalex.org/W2798854024","https://openalex.org/W2970208590","https://openalex.org/W4214717370","https://openalex.org/W4236415216","https://openalex.org/W6601979617","https://openalex.org/W6602828874","https://openalex.org/W6602985792","https://openalex.org/W6604693049","https://openalex.org/W6606774009","https://openalex.org/W6633092624","https://openalex.org/W6634944888","https://openalex.org/W6689871151","https://openalex.org/W6750731242","https://openalex.org/W6767357742"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,32,50,54,66,86,104,108,125,128,137,141,147,151],"use":[4,60,126],"of":[5,35,43,53,61,107,127,136,140,150],"a":[6,13,20,41,83,93,116,134],"dynamically":[7,81],"generated":[8,82],"exploration":[9,67,87,118],"rate":[10,68,88,119],"when":[11,115],"using":[12,92],"reinforcement":[14],"learning-based":[15],"game":[16,23,37,46,55,109,142,152],"agent":[17,38,110,153],"controller":[18,111],"within":[19,40],"dynamic":[21,51,117],"digital":[22],"environment.":[24],"Temporal":[25],"difference":[26],"learning":[27,91],"has":[28],"been":[29],"employed":[30],"for":[31,65,85],"real-time":[33],"generation":[34],"reactive":[36],"behaviors":[39],"variation":[42],"classic":[44],"arcade":[45],"Pac-Man.":[47],"Due":[48],"to":[49,90],"nature":[52],"environment":[56],"initial":[57],"experiments":[58,77],"made":[59],"static,":[62],"low":[63],"value":[64,84],"utilized":[69],"by":[70,133],"action":[71],"selection":[72],"during":[73],"learning.":[74],"However,":[75],"further":[76,144],"were":[78],"conducted":[79],"which":[80],"prior":[89],"genetic":[94,129],"algorithm.":[95],"Results":[96],"obtained":[97],"have":[98],"shown":[99],"that":[100],"an":[101],"improvement":[102],"in":[103,146],"overall":[105,148],"performance":[106,139,149],"may":[112,154],"be":[113,155],"achieved":[114],"is":[120,131],"used.":[121],"In":[122],"particular,":[123],"if":[124],"algorithm":[130],"controlled":[132],"measure":[135],"current":[138],"agent,":[143],"gains":[145],"achieved.":[156]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}