{"id":"https://openalex.org/W3015979606","doi":"https://doi.org/10.1109/tnnls.2020.2980743","title":"A3C-GS: Adaptive Moment Gradient Sharing With Locks for Asynchronous Actor\u2013Critic Agents","display_name":"A3C-GS: Adaptive Moment Gradient Sharing With Locks for Asynchronous Actor\u2013Critic Agents","publication_year":2020,"publication_date":"2020-04-10","ids":{"openalex":"https://openalex.org/W3015979606","doi":"https://doi.org/10.1109/tnnls.2020.2980743","mag":"3015979606","pmid":"https://pubmed.ncbi.nlm.nih.gov/32287019"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2980743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2980743","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5030904209","display_name":"Alfonso B. Labao","orcid":"https://orcid.org/0000-0001-5321-377X"},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Alfonso B. Labao","raw_affiliation_strings":["Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines"],"raw_orcid":"https://orcid.org/0000-0001-5321-377X","affiliations":[{"raw_affiliation_string":"Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012725992","display_name":"Mygel Andrei M. Martija","orcid":"https://orcid.org/0000-0001-5260-4429"},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Mygel Andrei M. Martija","raw_affiliation_strings":["Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines"],"raw_orcid":"https://orcid.org/0000-0001-5260-4429","affiliations":[{"raw_affiliation_string":"Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005869214","display_name":"Prospero C. Naval","orcid":"https://orcid.org/0000-0001-7140-1707"},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Prospero C. Naval","raw_affiliation_strings":["Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines"],"raw_orcid":"https://orcid.org/0000-0001-7140-1707","affiliations":[{"raw_affiliation_string":"Computer Vision and Machine Intelligence Group, University of the Philippines Diliman, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87074743"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":2.438,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.90925911,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"3","first_page":"1162","last_page":"1176"},"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":0.9890999794006348,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9872999787330627,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.805341362953186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6740536093711853},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5167588591575623},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4762401878833771},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44924044609069824},{"id":"https://openalex.org/keywords/contraction","display_name":"Contraction (grammar)","score":0.4426134526729584},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4323025941848755},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41928985714912415},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.4175240397453308},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4134121537208557},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3231866955757141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22504884004592896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20982950925827026},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15160465240478516}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.805341362953186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740536093711853},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5167588591575623},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4762401878833771},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44924044609069824},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.4426134526729584},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4323025941848755},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41928985714912415},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.4175240397453308},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4134121537208557},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3231866955757141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22504884004592896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20982950925827026},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15160465240478516},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.2980743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2980743","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32287019","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32287019","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2150468603","https://openalex.org/W2166706236","https://openalex.org/W2173564293","https://openalex.org/W2556958149","https://openalex.org/W2567015638","https://openalex.org/W2620671107","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2796202072","https://openalex.org/W2896073909","https://openalex.org/W2900919230","https://openalex.org/W2902408605","https://openalex.org/W2907217398","https://openalex.org/W2951799221","https://openalex.org/W2962902376","https://openalex.org/W2963095800","https://openalex.org/W2963423916","https://openalex.org/W2963959137","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964291307","https://openalex.org/W2969994581","https://openalex.org/W3103780890","https://openalex.org/W4297795161","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6684249991","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6730111887","https://openalex.org/W6731334075","https://openalex.org/W6738741286","https://openalex.org/W6741002519","https://openalex.org/W6744838376","https://openalex.org/W6747473740","https://openalex.org/W6766230978"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W4389391504","https://openalex.org/W2150611273","https://openalex.org/W4306904969","https://openalex.org/W4207086172","https://openalex.org/W2042919702","https://openalex.org/W4301410663","https://openalex.org/W4312472185"],"abstract_inverted_index":{"We":[0,56,136],"propose":[1],"an":[2],"asynchronous":[3,196],"gradient":[4,63,76,84,104,126],"sharing":[5,64,85,105],"mechanism":[6],"for":[7,32,38,111,185],"the":[8,21,29,36,45,49,53,62,79,101,116,130,156,194],"parallel":[9],"actor-critic":[10,198],"algorithms":[11],"with":[12,140],"improved":[13],"exploration":[14,172],"characteristics.":[15],"The":[16,72],"proposed":[17,153],"algorithm":[18,46,154],"(A3C-GS)":[19],"has":[20],"property":[22],"of":[23,69],"automatically":[24],"diversifying":[25],"worker":[26],"policies":[27,110],"in":[28,52,58,109,167,182],"short":[30,102],"term":[31],"exploration,":[33],"thereby":[34],"reducing":[35],"need":[37,180],"entropy":[39,162],"loss":[40],"terms.":[41],"Despite":[42,160],"policy":[43,51,132],"diversification,":[44],"converges":[47],"to":[48,129,174],"optimal":[50,131],"long":[54,117,186],"term.":[55],"show":[57],"our":[59,138],"analysis":[60],"that":[61,170,179],"operation":[65,86],"is":[66,82,133],"a":[67,83,120],"composition":[68],"two":[70,92],"contractions.":[71],"first":[73],"contraction":[74,81],"performs":[75],"computation,":[77],"while":[78],"second":[80],"coordinated":[87],"by":[88],"locks.":[89],"From":[90],"these":[91],"contractions,":[93],"certain":[94],"short-":[95],"and":[96,125,144,177],"long-term":[97],"properties":[98],"result.":[99],"For":[100],"term,":[103,118],"induces":[106],"temporary":[107],"heterogeneity":[108],"performing":[112],"needed":[113],"exploration.":[114],"In":[115],"under":[119],"suitably":[121],"small":[122],"learning":[123],"rate":[124],"clipping,":[127],"convergence":[128],"theoretically":[134],"guaranteed.":[135],"verify":[137],"results":[139],"several":[141],"high-dimensional":[142,168],"experiments":[143],"compare":[145],"A3C-GS":[146],"against":[147],"other":[148],"on-policy":[149],"policy-gradient":[150],"algorithms.":[151],"Our":[152],"achieved":[155],"highest":[157],"weighted":[158],"score.":[159],"lower":[161],"weights,":[163],"it":[164],"performed":[165,191],"well":[166],"environments":[169,184],"require":[171],"due":[173],"sparse":[175],"rewards":[176],"those":[178],"navigation":[181],"3-D":[183],"survival":[187],"tasks.":[188],"It":[189],"consistently":[190],"better":[192],"than":[193],"base":[195],"advantage":[197],"(A3C)":[199],"algorithm.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}