{"id":"https://openalex.org/W2111861907","doi":"https://doi.org/10.1109/iat.2003.1241115","title":"Q-learning automaton","display_name":"Q-learning automaton","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W2111861907","doi":"https://doi.org/10.1109/iat.2003.1241115","mag":"2111861907"},"language":"en","primary_location":{"id":"doi:10.1109/iat.2003.1241115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030340530","display_name":"Fei Qian","orcid":"https://orcid.org/0000-0002-0936-1043"},"institutions":[{"id":"https://openalex.org/I2321252","display_name":"Hiroshima Kokusai Gakuin University","ror":"https://ror.org/00mns7418","country_code":"JP","type":"education","lineage":["https://openalex.org/I2321252"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fei Qian","raw_affiliation_strings":["Faculty of Engineering, Hiroshima Kokusai Gakuin University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Hiroshima Kokusai Gakuin University, Japan","institution_ids":["https://openalex.org/I2321252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112205752","display_name":"Hironori Hirata","orcid":null},"institutions":[{"id":"https://openalex.org/I159385669","display_name":"Chiba University","ror":"https://ror.org/01hjzeq58","country_code":"JP","type":"education","lineage":["https://openalex.org/I159385669"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hironori Hirata","raw_affiliation_strings":["Graduate School of Science and Technology, Chiba University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Chiba University, Japan","institution_ids":["https://openalex.org/I159385669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.16292909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T12288","display_name":"Optimization and Search Problems","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.986299991607666,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8822376728057861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7784222364425659},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7061251401901245},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.6635467410087585},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.638995885848999},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5774141550064087},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.557458758354187},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5381141304969788},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5294960141181946},{"id":"https://openalex.org/keywords/deterministic-automaton","display_name":"Deterministic automaton","score":0.5168388485908508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4823819696903229},{"id":"https://openalex.org/keywords/timed-automaton","display_name":"Timed automaton","score":0.44816893339157104},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38947737216949463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34093159437179565},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13935482501983643}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8822376728057861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784222364425659},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7061251401901245},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.6635467410087585},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.638995885848999},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5774141550064087},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.557458758354187},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5381141304969788},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5294960141181946},{"id":"https://openalex.org/C194525867","wikidata":"https://www.wikidata.org/wiki/Q5265707","display_name":"Deterministic automaton","level":3,"score":0.5168388485908508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823819696903229},{"id":"https://openalex.org/C30788636","wikidata":"https://www.wikidata.org/wiki/Q7805517","display_name":"Timed automaton","level":3,"score":0.44816893339157104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38947737216949463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34093159437179565},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13935482501983643},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iat.2003.1241115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1497976081","https://openalex.org/W1500245617","https://openalex.org/W1537934887","https://openalex.org/W1538558539","https://openalex.org/W1548400210","https://openalex.org/W1641379095","https://openalex.org/W1979071892","https://openalex.org/W2021801581","https://openalex.org/W2107726111","https://openalex.org/W3036380436","https://openalex.org/W4214717370","https://openalex.org/W6629939909"],"related_works":["https://openalex.org/W97133087","https://openalex.org/W2040844343","https://openalex.org/W4243666448","https://openalex.org/W1533908838","https://openalex.org/W3104229711","https://openalex.org/W2145225595","https://openalex.org/W2152069471","https://openalex.org/W2573882791","https://openalex.org/W2478542454","https://openalex.org/W2764294725"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,53],"is":[2,25],"the":[3,44,62,66,71],"problem":[4],"faced":[5],"by":[6,31],"a":[7,19,51],"controller":[8],"that":[9,70],"must":[10],"learn":[11],"behavior":[12],"through":[13],"trial":[14],"and":[15,83],"error":[16],"interactions":[17],"with":[18,56],"dynamic":[20],"environment.":[21],"The":[22],"controller's":[23],"goal":[24],"to":[26,60],"maximize":[27],"reward":[28],"over":[29],"time,":[30],"producing":[32],"an":[33],"effective":[34],"mapping":[35],"of":[36,38,46,65,80],"states":[37],"actions":[39],"called":[40],"policy.":[41],"To":[42],"construct":[43],"model":[45],"such":[47],"systems,":[48],"we":[49],"present":[50],"generalized":[52],"automaton":[54],"approach":[55],"Q-learning":[57],"behaviors.":[58],"Compared":[59],"Q-learning,":[61],"computational":[63],"experiments":[64],"pursuit":[67],"problems":[68],"show":[69],"proposed":[72],"reinforcement":[73],"scheme":[74],"obtains":[75],"better":[76],"results":[77],"in":[78],"terms":[79],"convergence":[81],"speed":[82],"memory":[84],"size.":[85]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}