{"id":"https://openalex.org/W2344243474","doi":"https://doi.org/10.1109/tac.2015.2511930","title":"Mixed-Strategy Learning With Continuous Action Sets","display_name":"Mixed-Strategy Learning With Continuous Action Sets","publication_year":2015,"publication_date":"2015-12-23","ids":{"openalex":"https://openalex.org/W2344243474","doi":"https://doi.org/10.1109/tac.2015.2511930","mag":"2344243474"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2015.2511930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2015.2511930","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tac.2015.2511930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111423591","display_name":"Steven W. Perkins","orcid":null},"institutions":[{"id":"https://openalex.org/I2801520950","display_name":"At Bristol","ror":"https://ror.org/039fp5n52","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2801520950"]},{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steven Perkins","raw_affiliation_strings":["School of Mathematics, University of Bristol, Bristol, U.K","School of Mathematics [Bristol] (Bristol, BS8 1TW - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"School of Mathematics [Bristol] (Bristol, BS8 1TW - United Kingdom)","institution_ids":["https://openalex.org/I2801520950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018966648","display_name":"Panayotis Mertikopoulos","orcid":"https://orcid.org/0000-0003-2026-9616"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Panayotis Mertikopoulos","raw_affiliation_strings":["French National Center for Scientific Research (CNRS) and the Laboratoire d'Informatique de Grenoble, Grenoble, France","POLARIS - Performance analysis and optimization of LARge Infrastructures and Systems (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"French National Center for Scientific Research (CNRS) and the Laboratoire d'Informatique de Grenoble, Grenoble, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210104430"]},{"raw_affiliation_string":"POLARIS - Performance analysis and optimization of LARge Infrastructures and Systems (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9 - France)","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040706665","display_name":"David S. Leslie","orcid":"https://orcid.org/0000-0001-5253-7676"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David S. Leslie","raw_affiliation_strings":["Department of Mathematics and Statistics, Lancaster University, Lancaster, U.K","Department of Mathematics & Statistics [Lancaster] (Fylde College,\r\nLancaster University,\r\nLancaster, LA1 4YF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Lancaster University, Lancaster, U.K","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"Department of Mathematics & Statistics [Lancaster] (Fylde College,\r\nLancaster University,\r\nLancaster, LA1 4YF - United Kingdom)","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":{"value":2645,"currency":"USD","value_usd":2645},"fwci":8.3725,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97493783,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"62","issue":"1","first_page":"379","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7263344526290894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.61472088098526},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6133008003234863},{"id":"https://openalex.org/keywords/banach-space","display_name":"Banach space","score":0.5425196290016174},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5302174687385559},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47109732031822205},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4706294536590576},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46097245812416077},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4569121301174164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3700762093067169},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34722471237182617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32266855239868164},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.14824959635734558}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7263344526290894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.61472088098526},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6133008003234863},{"id":"https://openalex.org/C132954091","wikidata":"https://www.wikidata.org/wiki/Q194397","display_name":"Banach space","level":2,"score":0.5425196290016174},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5302174687385559},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47109732031822205},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4706294536590576},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46097245812416077},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4569121301174164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3700762093067169},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34722471237182617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32266855239868164},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.14824959635734558},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":3,"locations":[{"id":"doi:10.1109/tac.2015.2511930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2015.2511930","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:77057","is_oa":true,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/77057/1/PerkinsMertikopoulosLeslie_Revision2.pdf","pdf_url":"https://eprints.lancs.ac.uk/id/eprint/77057/1/PerkinsMertikopoulosLeslie_Revision2.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:HAL:hal-01382280v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01382280","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Automatic Control, 2017, 62 (1), pp.379 - 384. ⟨10.1109/TAC.2015.2511930⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/tac.2015.2511930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2015.2511930","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1104123382","display_name":null,"funder_award_id":"ANR-GAGA-13-JS01-0004-01","funder_id":"https://openalex.org/F4320322892","funder_display_name":"Centre National de la Recherche Scientifique"},{"id":"https://openalex.org/G1593487615","display_name":"Distributed learning algorithms orchestration for mobile networks resource management","funder_award_id":"ANR-13-INFR-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3199497286","display_name":"Decision making in an unstable world","funder_award_id":"EP/I032622/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4460811322","display_name":"SuSTaIn - Statistics underpinning Science, Technology and Industry","funder_award_id":"EP/D063485/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5561831765","display_name":null,"funder_award_id":"EP/D063485/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7256290259","display_name":"Geometric aspects of game theory","funder_award_id":"ANR-13-JS01-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G87568628","display_name":null,"funder_award_id":"EP/I032622/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320360","display_name":"University of Bristol","ror":"https://ror.org/0524sp257"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1491706803","https://openalex.org/W1605188341","https://openalex.org/W1966409365","https://openalex.org/W1967250398","https://openalex.org/W1971021761","https://openalex.org/W1972768959","https://openalex.org/W1990237136","https://openalex.org/W2008796819","https://openalex.org/W2026018281","https://openalex.org/W2030364091","https://openalex.org/W2034928886","https://openalex.org/W2034946992","https://openalex.org/W2058626062","https://openalex.org/W2066767736","https://openalex.org/W2067018002","https://openalex.org/W2070214254","https://openalex.org/W2087486726","https://openalex.org/W2094364653","https://openalex.org/W2095094403","https://openalex.org/W2096913736","https://openalex.org/W2108212877","https://openalex.org/W2112996088","https://openalex.org/W2116718598","https://openalex.org/W2117255278","https://openalex.org/W2122131925","https://openalex.org/W2124181538","https://openalex.org/W2127960170","https://openalex.org/W2128658178","https://openalex.org/W2134316447","https://openalex.org/W2135608404","https://openalex.org/W2135660060","https://openalex.org/W2146478733","https://openalex.org/W2147357149","https://openalex.org/W2161061197","https://openalex.org/W2169225433","https://openalex.org/W2169713291","https://openalex.org/W2176451521","https://openalex.org/W3022321359"],"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/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":{"Motivated":[0],"by":[1,106],"the":[2,9,50,54,69,73,79,103],"recent":[3],"applications":[4],"of":[5,11,19,56,72,81,102],"game-theoretical":[6],"learning":[7,38,91],"to":[8,61,76,87,99],"design":[10],"distributed":[12],"control":[13,20],"systems,":[14],"we":[15,52],"study":[16],"a":[17,62,89],"class":[18],"problems":[21],"that":[22,40,68],"can":[23],"be":[24],"formulated":[25],"as":[26],"potential":[27,82],"games":[28],"with":[29],"continuous":[30,45,70],"action":[31,46],"sets.":[32],"We":[33],"propose":[34],"an":[35],"actor-critic":[36],"reinforcement":[37],"algorithm":[39,92],"adapts":[41],"mixed":[42],"strategies":[43],"over":[44],"spaces.":[47],"To":[48],"analyze":[49],"algorithm,":[51],"extend":[53],"theory":[55],"finite-dimensional":[57],"two-timescale":[58],"stochastic":[59],"approximation":[60],"Banach":[63],"space":[64],"setting,":[65],"and":[66],"prove":[67],"dynamics":[71],"process":[74],"converge":[75],"equilibrium":[77],"in":[78,93],"case":[80],"games.":[83],"These":[84],"results":[85],"combine":[86],"give":[88],"provably-convergent":[90],"which":[94],"players":[95],"do":[96],"not":[97],"need":[98],"keep":[100],"track":[101],"controls":[104],"selected":[105],"other":[107],"agents.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}