{"id":"https://openalex.org/W4407786081","doi":"https://doi.org/10.1007/s10458-025-09695-8","title":"Low variance trust region optimization with independent actors and sequential updates in cooperative multi-agent reinforcement learning","display_name":"Low variance trust region optimization with independent actors and sequential updates in cooperative multi-agent reinforcement learning","publication_year":2025,"publication_date":"2025-02-20","ids":{"openalex":"https://openalex.org/W4407786081","doi":"https://doi.org/10.1007/s10458-025-09695-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-025-09695-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-025-09695-8","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-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/A5077010288","display_name":"Bang Giang Le","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Bang Giang Le","raw_affiliation_strings":["Human Machine Interaction Laboratory, VNU University of Engineering and Technology, 144 Xuan Thuy, Cau Giay, Hanoi, 100000, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, VNU University of Engineering and Technology, 144 Xuan Thuy, Cau Giay, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210128676"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053935756","display_name":"Viet Cuong Ta","orcid":"https://orcid.org/0000-0001-8058-5915"},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Viet Cuong Ta","raw_affiliation_strings":["Human Machine Interaction Laboratory, VNU University of Engineering and Technology, 144 Xuan Thuy, Cau Giay, Hanoi, 100000, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, VNU University of Engineering and Technology, 144 Xuan Thuy, Cau Giay, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210128676"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077010288"],"corresponding_institution_ids":["https://openalex.org/I4210128676"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01245093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9947999715805054,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7605353593826294},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7360407114028931},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.6540066003799438},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.624340295791626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5392552614212036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47233524918556213},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3235061764717102},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25174829363822937},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.24287596344947815},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12313106656074524},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08593815565109253}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7605353593826294},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7360407114028931},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.6540066003799438},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.624340295791626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5392552614212036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47233524918556213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3235061764717102},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25174829363822937},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.24287596344947815},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12313106656074524},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08593815565109253},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10458-025-09695-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-025-09695-8","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1631817276","display_name":null,"funder_award_id":"FA2386-24-1-4012","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6277145956","display_name":null,"funder_award_id":"FA2386-22-1-4026","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1575592356","https://openalex.org/W2158782408","https://openalex.org/W2411690432","https://openalex.org/W2560647685","https://openalex.org/W2617547828","https://openalex.org/W2619268125","https://openalex.org/W2623431351","https://openalex.org/W2763081248","https://openalex.org/W2788837839","https://openalex.org/W2807741983","https://openalex.org/W2963762747","https://openalex.org/W2990006450","https://openalex.org/W2990138404","https://openalex.org/W2995894173","https://openalex.org/W2998050631","https://openalex.org/W3039845099","https://openalex.org/W3082716386","https://openalex.org/W3100292177","https://openalex.org/W3127686539","https://openalex.org/W3163926178","https://openalex.org/W3169011731","https://openalex.org/W3200561352","https://openalex.org/W4226138304","https://openalex.org/W4281622133","https://openalex.org/W4286748781","https://openalex.org/W4287325269","https://openalex.org/W4298181618","https://openalex.org/W4365444201","https://openalex.org/W4375959468","https://openalex.org/W6638018090","https://openalex.org/W6758846586","https://openalex.org/W6800682094","https://openalex.org/W6803290710","https://openalex.org/W6849746254","https://openalex.org/W6851389620"],"related_works":["https://openalex.org/W2080108722","https://openalex.org/W2752681920","https://openalex.org/W1997473290","https://openalex.org/W2353911672","https://openalex.org/W2393042414","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2058731384","https://openalex.org/W2920061524","https://openalex.org/W4385488867"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
