{"id":"https://openalex.org/W2134993221","doi":"https://doi.org/10.1109/fuzzy.2011.6007675","title":"Fuzzy reinforcement learning control for decentralized partially observable Markov decision processes","display_name":"Fuzzy reinforcement learning control for decentralized partially observable Markov decision processes","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2134993221","doi":"https://doi.org/10.1109/fuzzy.2011.6007675","mag":"2134993221"},"language":"en","primary_location":{"id":"doi:10.1109/fuzzy.2011.6007675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)","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/A5023264501","display_name":"Rajneesh Sharma","orcid":"https://orcid.org/0000-0002-1619-1070"},"institutions":[{"id":"https://openalex.org/I36090812","display_name":"Netaji Subhas University of Technology","ror":"https://ror.org/01fczmh85","country_code":"IN","type":"education","lineage":["https://openalex.org/I36090812"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rajneesh Sharma","raw_affiliation_strings":["Instrumentation and Control Division, Netaji Subhas Institute of Technology, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Instrumentation and Control Division, Netaji Subhas Institute of Technology, New Delhi, India","institution_ids":["https://openalex.org/I36090812"]}]},{"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/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/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Matthijs T. J. Spaan","raw_affiliation_strings":["Institute of Systems and Robotics, Instituto Superior Technico, Lisboa, Portugal","Institute for Systems and Robotics , Instituto Superior Tecnico, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Institute of Systems and Robotics, Instituto Superior Technico, Lisboa, Portugal","institution_ids":["https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Institute for Systems and Robotics , Instituto Superior Tecnico, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023264501"],"corresponding_institution_ids":["https://openalex.org/I36090812"],"apc_list":null,"apc_paid":null,"fwci":0.4276,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73693999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"1422","last_page":"1429"},"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":0.9857000112533569,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9832000136375427,"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":0.8033784627914429},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7534996271133423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437400817871094},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7345768213272095},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.576664924621582},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5390879511833191},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5250247120857239},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5147719383239746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49963855743408203},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.48059770464897156},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.41774994134902954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3608081340789795},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34264737367630005},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.28208571672439575},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.17860662937164307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15533515810966492}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8033784627914429},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7534996271133423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437400817871094},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7345768213272095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.576664924621582},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5390879511833191},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5250247120857239},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5147719383239746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49963855743408203},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.48059770464897156},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.41774994134902954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3608081340789795},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34264737367630005},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28208571672439575},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.17860662937164307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15533515810966492},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fuzzy.2011.6007675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2011.6007675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1485268022","https://openalex.org/W1489867102","https://openalex.org/W1503287497","https://openalex.org/W1521003796","https://openalex.org/W1557517019","https://openalex.org/W1579579904","https://openalex.org/W1590292496","https://openalex.org/W1854776945","https://openalex.org/W2010124866","https://openalex.org/W2029280655","https://openalex.org/W2087992130","https://openalex.org/W2088956500","https://openalex.org/W2099618002","https://openalex.org/W2101036899","https://openalex.org/W2101957612","https://openalex.org/W2110906765","https://openalex.org/W2114032071","https://openalex.org/W2114245943","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2144283793","https://openalex.org/W2158305691","https://openalex.org/W2166533447","https://openalex.org/W2168359464","https://openalex.org/W2305205647","https://openalex.org/W2334782222","https://openalex.org/W2484215240","https://openalex.org/W3104860527","https://openalex.org/W4214717370","https://openalex.org/W6629361478","https://openalex.org/W6630029800","https://openalex.org/W6631137000","https://openalex.org/W6634752865","https://openalex.org/W6676769901","https://openalex.org/W6681633084"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"Decentralized":[0],"Partially":[1],"Observable":[2],"Markov":[3],"Decision":[4],"Processes":[5],"(Dec-POMDPs)":[6],"offer":[7],"a":[8,42,66,82,88,146],"powerful":[9],"platform":[10],"for":[11,25,52,138],"optimizing":[12],"sequential":[13],"decision":[14],"making":[15],"in":[16,87],"partially":[17],"observable":[18],"stochastic":[19],"environments.":[20],"However,":[21],"finding":[22],"optimal":[23],"solutions":[24],"Dec-POMDPs":[26],"is":[27],"known":[28],"to":[29,98],"be":[30],"intractable,":[31],"necessitating":[32],"approximate/suboptimal":[33],"approaches.":[34],"To":[35],"address":[36],"this":[37,39],"problem,":[38],"work":[40,77],"proposes":[41],"novel":[43],"fuzzy":[44,58,95,136],"reinforcement":[45],"learning":[46],"(RL)":[47],"based":[48,84,135],"game":[49,83,132],"theoretic":[50,133],"controller":[51,56],"Dec-POMDPs.":[53],"The":[54,72,123],"proposed":[55,108],"implements":[57],"RL":[59,85,134],"on":[60,110],"Dec-POMDPs,":[61,142],"which":[62],"are":[63,78],"modeled":[64],"as":[65],"sequence":[67],"of":[68,75,81,94,130,141],"Bayesian":[69],"games":[70],"(BG).":[71],"main":[73],"contributions":[74],"the":[76,79,92,101,107,126],"introduction":[80],"paradigm":[86],"Dec-POMDP":[89],"settings,":[90],"and":[91,114,128],"use":[93],"inference":[96],"systems":[97],"effectively":[99],"generalize":[100],"underlying":[102],"belief":[103],"space.":[104],"We":[105],"apply":[106],"technique":[109],"two":[111],"benchmark":[112],"problems":[113],"compare":[115],"results":[116,124],"against":[117],"state-of-the-art":[118],"Dec":[119],"POMDP":[120],"control":[121,137],"approach.":[122],"validate":[125],"feasibility":[127],"effectiveness":[129],"using":[131],"addressing":[139],"intractability":[140],"thus":[143],"opening":[144],"up":[145],"new":[147],"research":[148],"direction.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}