{"id":"https://openalex.org/W2006854168","doi":"https://doi.org/10.1109/tciaig.2012.2212279","title":"Bayesian-Game-Based Fuzzy Reinforcement Learning Control for Decentralized POMDPs","display_name":"Bayesian-Game-Based Fuzzy Reinforcement Learning Control for Decentralized POMDPs","publication_year":2012,"publication_date":"2012-08-08","ids":{"openalex":"https://openalex.org/W2006854168","doi":"https://doi.org/10.1109/tciaig.2012.2212279","mag":"2006854168"},"language":"en","primary_location":{"id":"doi:10.1109/tciaig.2012.2212279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tciaig.2012.2212279","pdf_url":null,"source":{"id":"https://openalex.org/S4210179349","display_name":"IEEE Transactions on Computational Intelligence and AI in Games","issn_l":"1943-068X","issn":["1943-068X","1943-0698"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Intelligence and AI in Games","raw_type":"journal-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/A5023264501","display_name":"Rajneesh Sharma","orcid":"https://orcid.org/0000-0002-1619-1070"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]},{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN","PT"],"is_corresponding":true,"raw_author_name":"Rajneesh Sharma","raw_affiliation_strings":["Indira Gandhi Institute of Technology, New Delhi, India","Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Indira Gandhi Institute of Technology, New Delhi, India","institution_ids":["https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075395956","display_name":"Matthijs T. J. Spaan","orcid":"https://orcid.org/0009-0002-2858-8611"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL","PT"],"is_corresponding":false,"raw_author_name":"Matthijs T. J. Spaan","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands","Institute for Systems and Robotics Instituto Superior T\u00e9cnico, Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Institute for Systems and Robotics Instituto Superior T\u00e9cnico, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023264501"],"corresponding_institution_ids":["https://openalex.org/I4210143260","https://openalex.org/I4210166615","https://openalex.org/I4387152517"],"apc_list":null,"apc_paid":null,"fwci":1.2844,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82683141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"4","first_page":"309","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.963100016117096,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8713115453720093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739923596382141},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6969631314277649},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6208270788192749},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5661557912826538},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5205634236335754},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48929497599601746},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42288094758987427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4109255075454712},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.27451014518737793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26086947321891785},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.23777449131011963},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.12786570191383362},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12084561586380005}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8713115453720093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739923596382141},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6969631314277649},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6208270788192749},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5661557912826538},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5205634236335754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48929497599601746},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42288094758987427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4109255075454712},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27451014518737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26086947321891785},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.23777449131011963},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.12786570191383362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12084561586380005},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tciaig.2012.2212279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tciaig.2012.2212279","pdf_url":null,"source":{"id":"https://openalex.org/S4210179349","display_name":"IEEE Transactions on Computational Intelligence and AI in Games","issn_l":"1943-068X","issn":["1943-068X","1943-0698"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Intelligence and AI in Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W12258761","https://openalex.org/W137519037","https://openalex.org/W156814138","https://openalex.org/W1015434911","https://openalex.org/W1501380298","https://openalex.org/W1501944800","https://openalex.org/W1513506787","https://openalex.org/W1536258751","https://openalex.org/W1557517019","https://openalex.org/W1561993501","https://openalex.org/W1579579904","https://openalex.org/W1588304026","https://openalex.org/W1589131899","https://openalex.org/W1590292496","https://openalex.org/W1590759229","https://openalex.org/W1602947059","https://openalex.org/W1854776945","https://openalex.org/W2004283713","https://openalex.org/W2010124866","https://openalex.org/W2029280655","https://openalex.org/W2032100464","https://openalex.org/W2087992130","https://openalex.org/W2088956500","https://openalex.org/W2099618002","https://openalex.org/W2101036899","https://openalex.org/W2102663728","https://openalex.org/W2114032071","https://openalex.org/W2114245943","https://openalex.org/W2131747355","https://openalex.org/W2132940773","https://openalex.org/W2134993221","https://openalex.org/W2137647991","https://openalex.org/W2141157184","https://openalex.org/W2143981651","https://openalex.org/W2149551746","https://openalex.org/W2162115371","https://openalex.org/W2162635261","https://openalex.org/W2164819104","https://openalex.org/W2164894752","https://openalex.org/W2166533447","https://openalex.org/W2168359464","https://openalex.org/W2295617766","https://openalex.org/W2305205647","https://openalex.org/W2334782222","https://openalex.org/W2480373768","https://openalex.org/W2484215240","https://openalex.org/W2612972698","https://openalex.org/W2760506156","https://openalex.org/W3104860527","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4298342474","https://openalex.org/W4388475847","https://openalex.org/W6600526285","https://openalex.org/W6606434334","https://openalex.org/W6629805071","https://openalex.org/W6629969969","https://openalex.org/W6630871465","https://openalex.org/W6633521956","https://openalex.org/W6634752865","https://openalex.org/W6635209275","https://openalex.org/W6635269564","https://openalex.org/W6635285615","https://openalex.org/W6636067836","https://openalex.org/W6672490383","https://openalex.org/W6679319433","https://openalex.org/W6679800765","https://openalex.org/W6721611342"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"This":[0,56],"paper":[1],"proposes":[2,58],"a":[3,23,43,69,86,89,119],"Bayesian-game-based":[4],"fuzzy":[5,64,81,90],"reinforcement":[6],"learning":[7],"(RL)":[8],"controller":[9,94,109,114,129],"for":[10,26,115,130,187],"decentralized":[11],"partially":[12,33],"observable":[13,34],"Markov":[14],"decision":[15,30],"processes":[16],"(Dec-POMDPs).":[17],"Dec-POMDPs":[18,116,134,142],"have":[19],"recently":[20],"emerged":[21],"as":[22,88,118],"powerful":[24,76],"platform":[25],"optimizing":[27],"multiagent":[28,157],"sequential":[29],"making":[31],"in":[32,68],"stochastic":[35],"environments.":[36],"However,":[37],"finding":[38],"exact":[39],"optimal":[40],"solutions":[41],"to":[42,83,95,103],"Dec-POMDP":[44,87,174,189],"is":[45],"provably":[46],"intractable":[47],"(NEXP-complete),":[48],"necessitating":[49],"the":[50,75,93,104,127,148,178],"use":[51],"of":[52,80,121,182],"approximate/suboptimal":[53],"solution":[54,61,102,175],"approaches.":[55],"approach":[57,150],"an":[59,100,111],"approximate":[60,101],"by":[62],"employing":[63,183],"inference":[65],"systems":[66,82],"(FISs)":[67],"game-based":[70],"RL":[71,113,186],"setting.":[72],"It":[73],"uses":[74],"universal":[77],"approximation":[78],"capability":[79],"compactly":[84],"represent":[85],"Dec-POMDP,":[91],"allowing":[92],"progressively":[96],"learn":[97],"and":[98,140,163,169,180],"update":[99],"underlying":[105],"Dec-POMDP.":[106],"The":[107],"proposed":[108,128,149],"envisages":[110],"FIS-based":[112,184],"modeled":[117],"sequence":[120],"Bayesian":[122],"games":[123],"(BGs).":[124],"We":[125,145],"implement":[126],"two":[131],"scenarios:":[132],"1)":[133,156],"with":[135],"free":[136],"communication":[137],"between":[138],"agents;":[139],"2)":[141,159],"without":[143],"communication.":[144],"empirically":[146],"evaluate":[147],"on":[151],"three":[152],"standard":[153],"benchmark":[154],"problems:":[155],"tiger;":[158],"multiaccess":[160],"broadcast":[161],"channel;":[162],"3)":[164],"recycling":[165],"robot.":[166],"Simulation":[167],"results":[168],"comparative":[170],"evaluation":[171],"against":[172],"other":[173],"approaches":[176],"elucidate":[177],"effectiveness":[179],"feasibility":[181],"game-theoretic":[185],"designing":[188],"controllers.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}