{"id":"https://openalex.org/W4407949323","doi":"https://doi.org/10.1109/cdc56724.2024.10886386","title":"Decentralized Multi-Agent Multi-Task Q-Learning with Function Approximation for POMDPs","display_name":"Decentralized Multi-Agent Multi-Task Q-Learning with Function Approximation for POMDPs","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949323","doi":"https://doi.org/10.1109/cdc56724.2024.10886386"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5055532417","display_name":"Milo\u0161 S. Stankovi\u0107","orcid":"https://orcid.org/0000-0001-9064-7059"},"institutions":[{"id":"https://openalex.org/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Milo\u0161 S. Stankovi\u0107","raw_affiliation_strings":["Singidunum University,Belgrade,Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singidunum University,Belgrade,Serbia","institution_ids":["https://openalex.org/I170253739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020552563","display_name":"Marko Beko","orcid":"https://orcid.org/0000-0001-7315-8739"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Marko Beko","raw_affiliation_strings":["Instituto de Telecomunica&#x00E7;&#x00F5;es, Instituto Superior T&#x00E9;cnico, Universidade de Lisboa,Lisbon,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, Instituto Superior T&#x00E9;cnico, Universidade de Lisboa,Lisbon,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018863930","display_name":"Srdjan Stankovi\u0107","orcid":"https://orcid.org/0000-0002-4795-494X"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Srdjan S. Stankovi\u0107","raw_affiliation_strings":["University of Belgrade,School of Electrical Engineering,Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Belgrade,School of Electrical Engineering,Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23791583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7680","last_page":"7685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.869700014591217,"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/T12676","display_name":"Machine Learning and ELM","score":0.869700014591217,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.7526999711990356,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14249","display_name":"Water Quality Monitoring and Analysis","score":0.7462000250816345,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701850950717926},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6590100526809692},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5887145400047302},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5183711647987366},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43012863397598267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34939831495285034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16630101203918457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07453504204750061},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06788262724876404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701850950717926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6590100526809692},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5887145400047302},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5183711647987366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43012863397598267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34939831495285034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16630101203918457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07453504204750061},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06788262724876404},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329307","display_name":"Science Fund of the Republic of Serbia","ror":null},{"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":25,"referenced_works":["https://openalex.org/W1098911146","https://openalex.org/W1539216098","https://openalex.org/W2071983464","https://openalex.org/W2077274021","https://openalex.org/W2124458906","https://openalex.org/W2125838338","https://openalex.org/W2132351269","https://openalex.org/W2145339207","https://openalex.org/W2151661095","https://openalex.org/W2169387407","https://openalex.org/W2267629510","https://openalex.org/W2605077367","https://openalex.org/W2765172389","https://openalex.org/W3135895062","https://openalex.org/W4214717370","https://openalex.org/W4321768300","https://openalex.org/W4381384918","https://openalex.org/W4381544449","https://openalex.org/W4400946884","https://openalex.org/W6600556750","https://openalex.org/W6629610187","https://openalex.org/W6674600207","https://openalex.org/W6739365718","https://openalex.org/W6740879895","https://openalex.org/W6754005058"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W4389443772","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W2548721895","https://openalex.org/W4303457083","https://openalex.org/W2373456246","https://openalex.org/W2131146434","https://openalex.org/W2951359407"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5,18,41,102,139],"novel":[6],"distributed":[7],"gradient-based":[8,87],"two-time-scale":[9],"algorithm":[10,32,75,89,135],"for":[11,49,108],"decentralized":[12],"multi-agent":[13],"multi-task":[14],"learning":[15,88],"(MTL)":[16],"using":[17,39],"linear":[19,103],"approximation":[20,66],"of":[21,38,51,57,63,68,143,155],"the":[22,36,52,58,64,69,95,112,118,128,133,144,153,156],"optimal":[23,65],"action":[24],"value":[25],"function":[26],"(Q":[27],"-function)":[28],"in":[29,40,114],"POMDPs.":[30],"The":[31,72],"is":[33,76,122],"based":[34,83],"on":[35,84],"idea":[37],"concurrent":[42],"way":[43],"recursive":[44],"Bayesian":[45],"state":[46,60],"belief":[47],"filters":[48],"estimation":[50],"system":[53],"model":[54],"parameters,":[55],"prediction":[56],"hidden":[59],"and":[61,100],"definition":[62],"parameters":[67,109],"local":[70,80],"Q-functions.":[71],"main":[73],"MTL":[74,119],"composed":[77],"of:":[78],"1)":[79],"parameter":[81,129],"updates":[82],"an":[85],"off-policy":[86],"with":[90],"target":[91],"policy":[92],"belonging":[93],"to":[94,116,138],"greedy":[96],"or":[97],"Gibbs":[98],"classes,":[99],"2)":[101],"stochastic":[104],"time-varying":[105],"consensus":[106],"scheme":[107],"shared":[110],"between":[111],"agents":[113],"order":[115],"achieve":[117],"goal.":[120],"It":[121],"proved,":[123],"under":[124],"general":[125],"assumptions,":[126],"that":[127],"estimates":[130],"generated":[131],"by":[132],"proposed":[134],"weakly":[136],"converge":[137],"bounded":[140],"invariant":[141],"set":[142],"corresponding":[145],"ordinary":[146],"differential":[147],"equations":[148],"(ODE).":[149],"Simulation":[150],"results":[151],"illustrate":[152],"effectiveness":[154],"algorithm.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
