{"id":"https://openalex.org/W4283730654","doi":"https://doi.org/10.1109/codit55151.2022.9804022","title":"Distributed Actor-Critic Learning Using Emphatic Weightings","display_name":"Distributed Actor-Critic Learning Using Emphatic Weightings","publication_year":2022,"publication_date":"2022-05-17","ids":{"openalex":"https://openalex.org/W4283730654","doi":"https://doi.org/10.1109/codit55151.2022.9804022"},"language":"en","primary_location":{"id":"doi:10.1109/codit55151.2022.9804022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit55151.2022.9804022","pdf_url":null,"source":{"id":"https://openalex.org/S4363607900","display_name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","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 8th International Conference on Control, Decision and Information Technologies (CoDIT)","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":["University Singidunum,Belgrade,Serbia","Vlatacom Institute, Belgrade, Serbia","University Singidunum, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Singidunum,Belgrade,Serbia","institution_ids":["https://openalex.org/I170253739"]},{"raw_affiliation_string":"Vlatacom Institute, Belgrade, Serbia","institution_ids":[]},{"raw_affiliation_string":"University Singidunum, 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/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"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT","RS"],"is_corresponding":false,"raw_author_name":"Srdjan S. Stankovi\u0107","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade,Serbia","School of Electrical Engineering, University of Belgrade, Serbia","Copelabs, Universidade Lusofona, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade,Serbia","institution_ids":["https://openalex.org/I4068193"]},{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]},{"raw_affiliation_string":"Copelabs, Universidade Lusofona, Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3114,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49006096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1167","last_page":"1172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.991100013256073,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.8254045248031616},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7191085815429688},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.6568483114242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5949450135231018},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.5416617393493652},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5288166999816895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5058023929595947},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49685409665107727},{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.49510231614112854},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.46726861596107483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.444056898355484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33978271484375},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.30368882417678833},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.18820565938949585},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.10884025692939758}],"concepts":[{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.8254045248031616},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7191085815429688},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.6568483114242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5949450135231018},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.5416617393493652},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5288166999816895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5058023929595947},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49685409665107727},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.49510231614112854},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.46726861596107483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.444056898355484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33978271484375},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.30368882417678833},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.18820565938949585},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.10884025692939758},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit55151.2022.9804022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit55151.2022.9804022","pdf_url":null,"source":{"id":"https://openalex.org/S4363607900","display_name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","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 8th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6120445142","display_name":"COPELABS - Cognitive and People-centric Computing R","funder_award_id":"UIDB/04111/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W359568995","https://openalex.org/W1499021337","https://openalex.org/W1547925194","https://openalex.org/W1941556277","https://openalex.org/W2009303086","https://openalex.org/W2044328306","https://openalex.org/W2075268401","https://openalex.org/W2077274021","https://openalex.org/W2094387729","https://openalex.org/W2099618002","https://openalex.org/W2106471678","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2267629510","https://openalex.org/W2286297039","https://openalex.org/W2559259492","https://openalex.org/W2765172389","https://openalex.org/W2768629321","https://openalex.org/W2776728688","https://openalex.org/W2788115019","https://openalex.org/W2788366696","https://openalex.org/W2892013712","https://openalex.org/W2947958009","https://openalex.org/W2951301202","https://openalex.org/W2953189830","https://openalex.org/W2953334758","https://openalex.org/W2963028406","https://openalex.org/W3010758700","https://openalex.org/W3103113203","https://openalex.org/W3135895062","https://openalex.org/W3153787838","https://openalex.org/W4206798850","https://openalex.org/W4210642114","https://openalex.org/W4306179383","https://openalex.org/W6600556750","https://openalex.org/W6612245137","https://openalex.org/W6632901617","https://openalex.org/W6640533243","https://openalex.org/W6677370284","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6695993938","https://openalex.org/W6745209853","https://openalex.org/W6746869544","https://openalex.org/W6748769517","https://openalex.org/W6749032143","https://openalex.org/W6760018431","https://openalex.org/W6762191990","https://openalex.org/W6807601316","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W3082668976","https://openalex.org/W2517973022","https://openalex.org/W1543121148","https://openalex.org/W1580703421","https://openalex.org/W2996841952","https://openalex.org/W2618518959","https://openalex.org/W2231364979","https://openalex.org/W4295745414","https://openalex.org/W4288093367","https://openalex.org/W4382202915"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"a":[3,34,44],"new":[4],"Actor-Critic":[5],"algorithm":[6,28,38,57],"is":[7,16,53],"proposed":[8,86],"for":[9],"distributed":[10,36],"off-policy":[11],"multi-agent":[12],"reinforcement":[13],"learning.":[14],"It":[15,52],"composed":[17],"of":[18,43,64,81,84],"the":[19,30,40,49,56,61,71,85],"Emphatic":[20],"Temporal":[21],"Difference":[22],"ETD":[23],"<tex":[24],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[25],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">${\\left(\\lambda":[26],"\\right)}$</tex>":[27],"(at":[29,48],"Critic":[31],"stage)":[32],"and":[33],"complementary":[35],"consensus-based":[37],"using":[39],"exact":[41],"gradients":[42],"given":[45],"criterion":[46],"function":[47],"Actor":[50],"stage).":[51],"demonstrated":[54],"that":[55],"converges":[58],"weakly":[59],"to":[60],"invariant":[62],"set":[63],"an":[65,79],"ordinary":[66],"differential":[67],"equation":[68],"(ODE)":[69],"characterizing":[70],"whole":[72],"algorithm.":[73,87],"Simulation":[74],"results":[75],"are":[76],"presented":[77],"as":[78],"illustration":[80],"high":[82],"efficiency":[83]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
