{"id":"https://openalex.org/W2121682629","doi":"https://doi.org/10.1109/irds.2002.1041521","title":"Learning mixed behaviours with parallel Q-learning","display_name":"Learning mixed behaviours with parallel Q-learning","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2121682629","doi":"https://doi.org/10.1109/irds.2002.1041521","mag":"2121682629"},"language":"en","primary_location":{"id":"doi:10.1109/irds.2002.1041521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","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/A5086574604","display_name":"Guillaume J. Laurent","orcid":"https://orcid.org/0000-0003-3586-4696"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210138517","display_name":"Observatoire de Besan\u00e7on","ror":"https://ror.org/032582s48","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210138517","https://openalex.org/I4210148025"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"G.J. Laurent","raw_affiliation_strings":["Laboratoire dE28099Automatique de Besan\u00e7on-UMR CNRS, Besancon, France","Lab. d'Automatique de Besancon, CNRS, Besancon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire dE28099Automatique de Besan\u00e7on-UMR CNRS, Besancon, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Lab. d'Automatique de Besancon, CNRS, Besancon, France","institution_ids":["https://openalex.org/I4210138517","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055567959","display_name":"Emmanuel Piat","orcid":"https://orcid.org/0009-0008-5374-4181"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210138517","display_name":"Observatoire de Besan\u00e7on","ror":"https://ror.org/032582s48","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210138517","https://openalex.org/I4210148025"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"E. Piat","raw_affiliation_strings":["Laboratoire dE28099Automatique de Besan\u00e7on-UMR CNRS, Besancon, France","Lab. d'Automatique de Besancon, CNRS, Besancon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire dE28099Automatique de Besan\u00e7on-UMR CNRS, Besancon, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Lab. d'Automatique de Besancon, CNRS, Besancon, France","institution_ids":["https://openalex.org/I4210138517","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086574604"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210138517"],"apc_list":null,"apc_paid":null,"fwci":2.7412,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91265796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1002","last_page":"1007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9966999888420105,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.978600025177002,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/q-learning","display_name":"Q-learning","score":0.8353424668312073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8206110000610352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7000555992126465},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5766348838806152},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5497518181800842},{"id":"https://openalex.org/keywords/parallel-manipulator","display_name":"Parallel manipulator","score":0.5012633800506592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48425623774528503},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4420834183692932},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3280560374259949},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2104533314704895}],"concepts":[{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.8353424668312073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8206110000610352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000555992126465},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5766348838806152},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5497518181800842},{"id":"https://openalex.org/C138094506","wikidata":"https://www.wikidata.org/wiki/Q12065277","display_name":"Parallel manipulator","level":3,"score":0.5012633800506592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48425623774528503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4420834183692932},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3280560374259949},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2104533314704895},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/irds.2002.1041521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1500245617","https://openalex.org/W1557517019","https://openalex.org/W1569296262","https://openalex.org/W1849208822","https://openalex.org/W2012036715","https://openalex.org/W2101767921","https://openalex.org/W2136082103","https://openalex.org/W2149276032","https://openalex.org/W2160371091","https://openalex.org/W3011120880","https://openalex.org/W6629939909","https://openalex.org/W6681745991","https://openalex.org/W6683821272"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","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","https://openalex.org/W2089415692"],"abstract_inverted_index":{"This":[0,16],"paper":[1],"presents":[2],"a":[3,9,22],"reinforcement":[4],"learning":[5],"algorithm":[6,17,58],"based":[7],"on":[8],"parallel":[10],"approach":[11],"of":[12],"the":[13,43,49,52],"Watkins's":[14],"Q-learning.":[15],"is":[18,29,59],"used":[19],"to":[20,30,61,75],"control":[21],"two":[23],"axis":[24],"micro-manipulator":[25],"system.":[26],"The":[27,46],"aim":[28],"learn":[31,62],"complex":[32],"behaviour":[33],"such":[34],"as":[35],"reaching":[36],"target":[37],"positions":[38],"and":[39,48,66],"avoiding":[40],"obstacles":[41],"at":[42],"same":[44],"time.":[45],"simulations":[47],"tests":[50],"with":[51,73],"real":[53],"manipulator":[54],"show":[55],"that":[56,67],"this":[57],"able":[60],"simultaneously":[63],"opposite":[64],"behaviours":[65],"it":[68],"generates":[69],"interesting":[70],"action":[71],"policies":[72],"regard":[74],"global":[76],"path":[77],"optimization.":[78]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}