{"id":"https://openalex.org/W4315472286","doi":"https://doi.org/10.1109/cdc51059.2022.9992951","title":"Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus","display_name":"Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315472286","doi":"https://doi.org/10.1109/cdc51059.2022.9992951"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992951","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992951","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st 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":true,"raw_author_name":"Milos S. Stankovic","raw_affiliation_strings":["University Singidunum,Belgrade,Serbia","University Singidunum, Belgrade, Serbia","Vlatacom Institute, Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"University Singidunum,Belgrade,Serbia","institution_ids":["https://openalex.org/I170253739"]},{"raw_affiliation_string":"University Singidunum, Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]},{"raw_affiliation_string":"Vlatacom Institute, Belgrade, Serbia","institution_ids":[]}]},{"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":["Universidade de Lisboa,Instituto de Telecomunicações, Instituto Superior Técnico,Lisbon,Portugal"],"affiliations":[{"raw_affiliation_string":"Universidade de Lisboa,Instituto de Telecomunicações, Instituto Superior Técnico,Lisbon,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518778","display_name":"Nemanja Ili\u0107","orcid":"https://orcid.org/0000-0002-2763-2564"},"institutions":[{"id":"https://openalex.org/I4210158487","display_name":"Technical College of Applied Sciences","ror":"https://ror.org/051dyvc17","country_code":"RS","type":"education","lineage":["https://openalex.org/I4210158487"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Nemanja Ilic","raw_affiliation_strings":["College of Applied Technical Sciences,Kruševac,Serbia"],"affiliations":[{"raw_affiliation_string":"College of Applied Technical Sciences,Kruševac,Serbia","institution_ids":["https://openalex.org/I4210158487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103386989","display_name":"Srdjan S. Stankovi\u0107","orcid":null},"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. Stankovic","raw_affiliation_strings":["University of Belgrade,School of Electrical Engineering,Serbia","School of Electrical Engineering, University of Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"University of Belgrade,School of Electrical Engineering,Serbia","institution_ids":["https://openalex.org/I4068193"]},{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055532417"],"corresponding_institution_ids":["https://openalex.org/I170253739"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53490627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"4591","last_page":"4596"},"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":0.9962999820709229,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8738206028938293},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.7428070306777954},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7021570205688477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6177558898925781},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6143994331359863},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.6121093034744263},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.540996789932251},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4925766587257385},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4814373850822449},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4749700725078583},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4228706955909729},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.42107051610946655},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4112473428249359},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3956904709339142},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3347504138946533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2966269850730896},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.20192953944206238},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16660812497138977},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.13260120153427124}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8738206028938293},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.7428070306777954},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7021570205688477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6177558898925781},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6143994331359863},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.6121093034744263},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.540996789932251},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4925766587257385},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4814373850822449},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4749700725078583},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4228706955909729},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.42107051610946655},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4112473428249359},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3956904709339142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3347504138946533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2966269850730896},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.20192953944206238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16660812497138977},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.13260120153427124},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992951","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992951","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st 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}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1098911146","https://openalex.org/W1498711961","https://openalex.org/W1499021337","https://openalex.org/W1941556277","https://openalex.org/W2009303086","https://openalex.org/W2077274021","https://openalex.org/W2094364653","https://openalex.org/W2094387729","https://openalex.org/W2106471678","https://openalex.org/W2139948925","https://openalex.org/W2145339207","https://openalex.org/W2267629510","https://openalex.org/W2286297039","https://openalex.org/W2559259492","https://openalex.org/W2765172389","https://openalex.org/W2776728688","https://openalex.org/W2788366696","https://openalex.org/W2892013712","https://openalex.org/W2951301202","https://openalex.org/W2953189830","https://openalex.org/W2963028406","https://openalex.org/W2968526727","https://openalex.org/W3010758700","https://openalex.org/W3036329728","https://openalex.org/W3103113203","https://openalex.org/W3135895062","https://openalex.org/W3153787838","https://openalex.org/W3176552354","https://openalex.org/W4206372735","https://openalex.org/W4210642114","https://openalex.org/W4214717370","https://openalex.org/W4283730654","https://openalex.org/W4312277898","https://openalex.org/W6640533243","https://openalex.org/W6677370284","https://openalex.org/W6683001934","https://openalex.org/W6695993938","https://openalex.org/W6746869544","https://openalex.org/W6748769517","https://openalex.org/W6749032143","https://openalex.org/W6760018431","https://openalex.org/W6762191990","https://openalex.org/W6767091432","https://openalex.org/W6778995641"],"related_works":["https://openalex.org/W3206576350","https://openalex.org/W2772472730","https://openalex.org/W3008618380","https://openalex.org/W2964123095","https://openalex.org/W2473364827","https://openalex.org/W2107850435","https://openalex.org/W359568995","https://openalex.org/W2080453320","https://openalex.org/W2165905123","https://openalex.org/W2575667675"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,37,45],"new":[4],"distributed":[5,24],"multi-agent":[6],"off-policy":[7],"Actor-Critic":[8],"algorithm":[9,28,62,74,101],"for":[10,59],"collaborative":[11],"multitask":[12],"reinforcement":[13],"learning":[14],"is":[15,20,34,67,85,103],"proposed.":[16],"The":[17,69],"Critic":[18],"stage":[19,33,66],"based":[21],"on":[22],"the":[23,31,55,60,64,73,76,91,100],"gradient":[25,50],"temporal":[26],"difference":[27],"GTD(1),":[29],"while":[30],"Actor":[32,65],"derived":[35,61],"from":[36],"predefined":[38],"global":[39],"criterion":[40],"function":[41],"and":[42,109],"consists":[43],"of":[44,72,78,81,99],"complementary":[46],"consensus-based":[47],"exact":[48],"policy":[49],"algorithm.":[51],"A":[52],"proof":[53],"that":[54],"Feller-Markov":[56],"properties":[57,102],"hold":[58],"at":[63],"derived.":[68],"weak":[70],"convergence":[71],"to":[75],"set":[77],"stationary":[79],"points":[80],"an":[82],"attached":[83],"ODE":[84],"proved":[86],"under":[87],"mild":[88],"conditions":[89],"using":[90],"two-time-scale":[92],"stochastic":[93],"approximation":[94],"arguments.":[95],"An":[96],"experimental":[97],"verification":[98],"given,":[104],"demonstrating":[105],"its":[106],"high":[107],"efficiency":[108],"practical":[110],"applicability.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}