{"id":"https://openalex.org/W2075874606","doi":"https://doi.org/10.1137/130936488","title":"Reinforcement Learning with Restrictions on the Action Set","display_name":"Reinforcement Learning with Restrictions on the Action Set","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2075874606","doi":"https://doi.org/10.1137/130936488","mag":"2075874606"},"language":"en","primary_location":{"id":"doi:10.1137/130936488","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130936488","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1306.2918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074994019","display_name":"Mario Bravo","orcid":"https://orcid.org/0000-0002-4312-9600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mario Bravo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mathieu Faure","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Faure","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1149,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8177106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"53","issue":"1","first_page":"287","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.65829998254776,"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"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.65829998254776,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16760000586509705,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.11680000275373459,"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/stochastic-game","display_name":"Stochastic game","score":0.8107541799545288},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.680200457572937},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6490117907524109},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.6273113489151001},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.621893048286438},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.6095411777496338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6038314700126648},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5624041557312012},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.5218345522880554},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.4741365611553192},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.465810090303421},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3470466136932373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.29204803705215454},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2907456159591675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24989691376686096}],"concepts":[{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.8107541799545288},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.680200457572937},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6490117907524109},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.6273113489151001},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.621893048286438},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.6095411777496338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6038314700126648},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5624041557312012},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.5218345522880554},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.4741365611553192},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.465810090303421},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3470466136932373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29204803705215454},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2907456159591675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24989691376686096},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1137/130936488","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130936488","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1306.2918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.2918","pdf_url":"https://arxiv.org/pdf/1306.2918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:HAL:hal-01457301v1","is_oa":false,"landing_page_url":"https://amu.hal.science/hal-01457301","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":"SIAM Journal on Control and Optimization, 2015, 53 (1), pp.287--312. ⟨10.1137/130936488⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repositorio.uchile.cl:2250/132415","is_oa":true,"landing_page_url":"https://repositorio.uchile.cl/handle/2250/132415","pdf_url":null,"source":{"id":"https://openalex.org/S4306481413","display_name":"Universidad de Chile","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Art\u00edculo de revista"},{"id":"doi:10.48550/arxiv.1306.2918","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1306.2918","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1306.2918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.2918","pdf_url":"https://arxiv.org/pdf/1306.2918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1099509903","display_name":null,"funder_award_id":"P-05-004-F","funder_id":"https://openalex.org/F4320327624","funder_display_name":"Instituto de Sistemas Complejos de Ingenier\u00eda"},{"id":"https://openalex.org/G5503664190","display_name":null,"funder_award_id":"FBO16","funder_id":"https://openalex.org/F4320327624","funder_display_name":"Instituto de Sistemas Complejos de Ingenier\u00eda"},{"id":"https://openalex.org/G5777107276","display_name":null,"funder_award_id":"FBO16","funder_id":"https://openalex.org/F4320334812","funder_display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica"},{"id":"https://openalex.org/G6095817613","display_name":null,"funder_award_id":"P-05-004-F","funder_id":"https://openalex.org/F4320334812","funder_display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica"}],"funders":[{"id":"https://openalex.org/F4320327624","display_name":"Instituto de Sistemas Complejos de Ingenier\u00eda","ror":"https://ror.org/04wnc7270"},{"id":"https://openalex.org/F4320334812","display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1491706803","https://openalex.org/W1499021337","https://openalex.org/W1514218977","https://openalex.org/W1564229172","https://openalex.org/W1568229137","https://openalex.org/W1605188341","https://openalex.org/W1964757264","https://openalex.org/W1967250398","https://openalex.org/W1983774541","https://openalex.org/W1989107041","https://openalex.org/W1995622844","https://openalex.org/W2005228957","https://openalex.org/W2067399933","https://openalex.org/W2070214254","https://openalex.org/W2087486726","https://openalex.org/W2091328462","https://openalex.org/W2093074200","https://openalex.org/W2096565876","https://openalex.org/W2096702014","https://openalex.org/W2096913736","https://openalex.org/W2102704407","https://openalex.org/W2108212877","https://openalex.org/W2118247617","https://openalex.org/W2126776273","https://openalex.org/W2133073047","https://openalex.org/W2141754579","https://openalex.org/W2149254401","https://openalex.org/W2167425257","https://openalex.org/W2167957526","https://openalex.org/W2169225433","https://openalex.org/W2237678354","https://openalex.org/W3099151731","https://openalex.org/W4214854436"],"related_works":["https://openalex.org/W4302081789","https://openalex.org/W3206434681","https://openalex.org/W1991899349","https://openalex.org/W2809791077","https://openalex.org/W2963864634","https://openalex.org/W3125633875","https://openalex.org/W4300895205","https://openalex.org/W3109452493","https://openalex.org/W4309575807","https://openalex.org/W1989107041"],"abstract_inverted_index":{"Consider":[0],"a":[1,66],"two-player":[2],"normal-form":[3],"game":[4],"repeated":[5],"over":[6],"time.":[7],"We":[8,26,72],"introduce":[9],"an":[10],"adaptive":[11],"learning":[12],"procedure,":[13],"where":[14,94],"the":[15,42,75,82],"players":[16],"only":[17],"observe":[18],"their":[19,33,53,61,69],"own":[20,34,54],"realized":[21],"payoff":[22,35],"at":[23,58],"each":[24,59],"stage.":[25],"assume":[27,47],"that":[28,48,74],"agents":[29],"do":[30],"not":[31],"know":[32],"function":[36],"and":[37,89,92],"have":[38,50],"no":[39],"information":[40],"on":[41,52],"other":[43],"player.":[44],"Furthermore,":[45],"we":[46],"they":[49],"restrictions":[51],"actions":[55],"such":[56],"that,":[57],"stage,":[60],"choice":[62],"is":[63],"limited":[64],"to":[65,81],"subset":[67],"of":[68,78,84],"action":[70],"set.":[71],"prove":[73],"empirical":[76],"distributions":[77],"play":[79],"converge":[80],"set":[83],"Nash":[85],"equilibria":[86],"for":[87],"zero-sum":[88],"potential":[90],"games,":[91],"games":[93],"one":[95],"player":[96],"has":[97],"two":[98],"actions.":[99]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2016-06-24T00:00:00"}