{"id":"https://openalex.org/W3144388779","doi":"https://doi.org/10.1109/wsc.2011.6148098","title":"A sampled fictitious play based learning algorithm for infinite horizon Markov Decision Processes","display_name":"A sampled fictitious play based learning algorithm for infinite horizon Markov Decision Processes","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W3144388779","doi":"https://doi.org/10.1109/wsc.2011.6148098","mag":"3144388779"},"language":"en","primary_location":{"id":"doi:10.1109/wsc.2011.6148098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc.2011.6148098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Winter Simulation Conference (WSC)","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/A5045001171","display_name":"Esra Sisikoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Esra Sisikoglu","raw_affiliation_strings":["The University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"The University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013764577","display_name":"Marina A. Epelman","orcid":"https://orcid.org/0000-0002-0056-1583"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marina A. Epelman","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102899461","display_name":"Robert L. Smith","orcid":"https://orcid.org/0000-0002-4669-8948"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert L. Smith","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045001171"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82349179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4086","last_page":"4097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9959999918937683,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9945999979972839,"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/markov-decision-process","display_name":"Markov decision process","score":0.821590781211853},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.624691367149353},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5827996730804443},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5493254661560059},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5488749146461487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5417308211326599},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.519029974937439},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4800735116004944},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46939176321029663},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46490204334259033},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4588930606842041},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4493638575077057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.441644549369812},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3819068670272827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32149580121040344},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08649912476539612}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.821590781211853},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.624691367149353},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5827996730804443},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5493254661560059},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5488749146461487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5417308211326599},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.519029974937439},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4800735116004944},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46939176321029663},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46490204334259033},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4588930606842041},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4493638575077057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.441644549369812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3819068670272827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32149580121040344},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08649912476539612},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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":2,"locations":[{"id":"doi:10.1109/wsc.2011.6148098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc.2011.6148098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.416.4820","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.4820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.informs-sim.org/wsc11papers/364.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W157428806","https://openalex.org/W1542078623","https://openalex.org/W2016647253","https://openalex.org/W2055537715","https://openalex.org/W2085697350","https://openalex.org/W2106647675","https://openalex.org/W2118247617","https://openalex.org/W2140332127","https://openalex.org/W2146917784","https://openalex.org/W2149254401","https://openalex.org/W2150339816","https://openalex.org/W2487144912","https://openalex.org/W2489939061","https://openalex.org/W4205326910","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W6606417803","https://openalex.org/W6634528131","https://openalex.org/W6680589885"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2808418668","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Using":[0],"Sampled":[1,9],"Fictitious":[2,10],"Play":[3,11],"(SFP)":[4],"concepts,":[5],"we":[6],"develop":[7],"SFPL:":[8],"Learning":[12],"-":[13],"a":[14],"learning":[15,109],"algorithm":[16,99],"for":[17,93],"solving":[18],"discounted":[19],"homogeneous":[20],"Markov":[21],"Decision":[22],"Problems":[23],"where":[24],"the":[25,41,50,53,58,67,71,75,85,94],"transition":[26,55,79],"probabilities":[27,56],"are":[28],"unknown":[29,54],"and":[30,57,63,113],"need":[31],"to":[32],"be":[33],"learned":[34],"via":[35],"simulation":[36],"or":[37],"direct":[38],"observation":[39],"of":[40,52,60,73,88],"system":[42],"in":[43,66],"real":[44],"time.":[45],"Thus,":[46],"SFPL":[47],"simultaneously":[48],"updates":[49],"estimates":[51,59,92],"optimal":[61,64,90],"value":[62],"action":[65,76,91],"observed":[68],"state.":[69,96],"In":[70],"spirit":[72],"SFP,":[74],"after":[77],"each":[78],"is":[80,100],"selected":[81],"by":[82],"sampling":[83],"from":[84],"empirical":[86],"distribution":[87],"previous":[89],"current":[95],"The":[97],"resulting":[98],"provably":[101],"convergent.":[102],"We":[103],"compare":[104],"its":[105],"performance":[106],"with":[107],"other":[108],"methods,":[110],"including":[111],"SARSA":[112],"Q-learning.":[114]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}