{"id":"https://openalex.org/W4200113240","doi":"https://doi.org/10.1016/j.automatica.2021.110092","title":"Fully asynchronous policy evaluation in distributed reinforcement learning over networks","display_name":"Fully asynchronous policy evaluation in distributed reinforcement learning over networks","publication_year":2021,"publication_date":"2021-12-16","ids":{"openalex":"https://openalex.org/W4200113240","doi":"https://doi.org/10.1016/j.automatica.2021.110092","mag":"3006742932"},"language":"en","primary_location":{"id":"doi:10.1016/j.automatica.2021.110092","doi":"https://doi.org/10.1016/j.automatica.2021.110092","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.automatica.2021.110092","pdf_url":null,"source":{"id":"https://openalex.org/S51360982","display_name":"Automatica","issn_l":"0005-1098","issn":["0005-1098","1873-2836"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatica","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.00433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064528716","display_name":"Xingyu Sha","orcid":"https://orcid.org/0000-0001-9673-302X","observed_orcids":["https://orcid.org/0000-0001-9673-302X"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Sha","raw_affiliation_strings":["Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349811","display_name":"Jiaqi Zhang","orcid":"https://orcid.org/0000-0002-8833-1714","observed_orcids":["https://orcid.org/0000-0002-8833-1714"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Zhang","raw_affiliation_strings":["Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088962631","display_name":"Keyou You","orcid":"https://orcid.org/0000-0003-4355-5340","observed_orcids":["https://orcid.org/0000-0003-4355-5340"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Keyou You","raw_affiliation_strings":["Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581","observed_orcids":["https://orcid.org/0000-0002-7446-7581"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875","observed_orcids":["https://orcid.org/0000-0003-4406-7875"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Ba\u015far","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana\u2013Champaign, Urbana, IL 61801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana\u2013Champaign, Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088962631"],"corresponding_institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"],"apc_list":{"value":3010,"currency":"USD","value_usd":3010},"apc_paid":null,"fwci":1.4603,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.83775501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"136","issue":null,"first_page":"110092","last_page":"110092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9223999977111816,"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":0.9223999977111816,"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":0.06080000102519989,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/distributed-reinforcement-learning","display_name":"distributed reinforcement learning","score":0.968999981880188},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.9399999976158142},{"id":"https://openalex.org/keywords/asynchronous-updates","display_name":"asynchronous updating","score":0.5839999914169312},{"id":"https://openalex.org/keywords/peer-to-peer-networks","display_name":"peer-to-peer networks","score":0.9190000295639038},{"id":"https://openalex.org/keywords/linear-convergence","display_name":"linear convergence","score":0.6140000224113464},{"id":"https://openalex.org/keywords/straggler-nodes","display_name":"straggler nodes","score":0.8299999833106995},{"id":"https://openalex.org/keywords/value-function-estimation","display_name":"value function estimation","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8428760766983032},{"id":"https://openalex.org/C62989814","wikidata":"https://www.wikidata.org/wiki/Q854648","display_name":"Gossip","level":2,"score":0.8029356002807617},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.757714033126831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733721911907196},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.597490668296814},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5851266384124756},{"id":"https://openalex.org/C145928361","wikidata":"https://www.wikidata.org/wiki/Q5587504","display_name":"Gossip protocol","level":3,"score":0.5365412831306458},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4934617578983307},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.46155309677124023},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4308483302593231},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4292127788066864},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4277552366256714},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3933331370353699},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27341318130493164},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2638384699821472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19299688935279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16854211688041687},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07909691333770752},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.automatica.2021.110092","doi":"https://doi.org/10.1016/j.automatica.2021.110092","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.automatica.2021.110092","pdf_url":null,"source":{"id":"https://openalex.org/S51360982","display_name":"Automatica","issn_l":"0005-1098","issn":["0005-1098","1873-2836"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatica","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2003.00433","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.00433","pdf_url":"https://arxiv.org/pdf/2003.00433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3006742932","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2003.00433","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.00433","doi":"https://doi.org/10.48550/arxiv.2003.00433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.00433","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.00433","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.00433","pdf_url":"https://arxiv.org/pdf/2003.00433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1850434087","display_name":null,"funder_award_id":"62033006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200113240.pdf","grobid_xml":"https://content.openalex.org/works/W4200113240.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522371103","https://openalex.org/W1603765807","https://openalex.org/W1791038712","https://openalex.org/W1918371733","https://openalex.org/W1977655452","https://openalex.org/W2016054326","https://openalex.org/W2075268401","https://openalex.org/W2093777540","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2216483973","https://openalex.org/W2260756217","https://openalex.org/W2276974598","https://openalex.org/W2395575420","https://openalex.org/W2436219157","https://openalex.org/W2594203335","https://openalex.org/W2737743075","https://openalex.org/W2765170276","https://openalex.org/W2766447205","https://openalex.org/W2786036274","https://openalex.org/W2788115019","https://openalex.org/W2792751837","https://openalex.org/W2793522527","https://openalex.org/W2805324628","https://openalex.org/W2806414180","https://openalex.org/W2811201469","https://openalex.org/W2885464805","https://openalex.org/W2901992463","https://openalex.org/W2911446756","https://openalex.org/W2913483008","https://openalex.org/W2914757193","https://openalex.org/W2944956041","https://openalex.org/W2951923023","https://openalex.org/W2952215077","https://openalex.org/W2956537605","https://openalex.org/W2962970252","https://openalex.org/W2963228337","https://openalex.org/W2963385547","https://openalex.org/W2963649943","https://openalex.org/W2963985863","https://openalex.org/W2966162740","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W2991772480","https://openalex.org/W3006548771","https://openalex.org/W3009520628","https://openalex.org/W3010781917","https://openalex.org/W3049494490","https://openalex.org/W3097497066","https://openalex.org/W3098048099","https://openalex.org/W3120837913","https://openalex.org/W3163894240","https://openalex.org/W4214717370","https://openalex.org/W4230581820"],"related_works":["https://openalex.org/W3006742932","https://openalex.org/W3203898015","https://openalex.org/W4415336514","https://openalex.org/W4411166154","https://openalex.org/W3163894240","https://openalex.org/W3108171015","https://openalex.org/W3120837913","https://openalex.org/W7160559245","https://openalex.org/W4409156116","https://openalex.org/W2904435756"],"abstract_inverted_index":null,"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":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2021-12-31T00:00:00"}
