{"id":"https://openalex.org/W3015291918","doi":"https://doi.org/10.1109/icassp40776.2020.9053534","title":"Stabilizing Multi-Agent Deep Reinforcement Learning by Implicitly Estimating Other Agents\u2019 Behaviors","display_name":"Stabilizing Multi-Agent Deep Reinforcement Learning by Implicitly Estimating Other Agents\u2019 Behaviors","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015291918","doi":"https://doi.org/10.1109/icassp40776.2020.9053534","mag":"3015291918"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.lsu.edu/eecs_pubs/1170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067942871","display_name":"Yue Jin","orcid":"https://orcid.org/0000-0002-0344-4868"},"institutions":[{"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":"Yue Jin","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012143414","display_name":"Shuangqing Wei","orcid":"https://orcid.org/0000-0001-5913-1441"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuangqing Wei","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Louisiana State University, Baton Rouge, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Louisiana State University, Baton Rouge, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347994","display_name":"Jian Yuan","orcid":"https://orcid.org/0000-0001-9734-6056"},"institutions":[{"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":"Jian Yuan","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441855","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0002-6465-7437"},"institutions":[{"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":"Xudong Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407035","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-7427-793X"},"institutions":[{"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":"Chao Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067942871"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5437,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7279163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"518","issue":null,"first_page":"3547","last_page":"3551"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.995199978351593,"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":0.9907000064849854,"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":0.858210027217865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695445716381073},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5819535851478577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49738290905952454},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4426150918006897},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14159277081489563},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05272945761680603}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858210027217865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695445716381073},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5819535851478577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49738290905952454},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4426150918006897},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14159277081489563},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05272945761680603}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.lsu.edu:eecs_pubs-2172","is_oa":true,"landing_page_url":"https://digitalcommons.lsu.edu/eecs_pubs/1170","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-2172","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/1170","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.lsu.edu:eecs_pubs-2172","is_oa":true,"landing_page_url":"https://digitalcommons.lsu.edu/eecs_pubs/1170","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2097498347","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2592798481","https://openalex.org/W2604873668","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2894976951","https://openalex.org/W2937310911","https://openalex.org/W2951896791","https://openalex.org/W2962938168","https://openalex.org/W2963407617","https://openalex.org/W2963658727","https://openalex.org/W2966371608","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W6637967152","https://openalex.org/W6674705169","https://openalex.org/W6734678876","https://openalex.org/W6736572398","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6755069753"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,62],"(DRL)":[3],"is":[4,46,72],"able":[5],"to":[6,21,50,53,100],"learn":[7,119],"control":[8],"policies":[9,45,59],"for":[10],"many":[11],"complicated":[12],"tasks,":[13],"but":[14],"it's":[15],"power":[16],"has":[17],"not":[18],"been":[19],"unleashed":[20],"handle":[22],"multi-agent":[23,54],"circumstances.":[24],"Independent":[25],"learning,":[26],"where":[27,90],"each":[28,68,91,116],"agent":[29,92,117],"treats":[30],"others":[31],"as":[32,61],"part":[33],"of":[34,67,97,113,143],"the":[35,65,70,110,135,139],"environment":[36,71],"and":[37,137,147],"learns":[38],"its":[39,102,120],"own":[40,103],"policy":[41,104,121,148],"without":[42],"considering":[43],"others'":[44,98,114],"a":[47,87,123],"simple":[48],"way":[49],"apply":[51],"DRL":[52,77],"tasks.":[55],"However,":[56],"since":[57],"agents'":[58],"change":[60],"proceeds,":[63],"from":[64],"perspective":[66],"agent,":[69],"non-stationary,":[73],"which":[74],"makes":[75],"conventional":[76],"methods":[78],"inefficient.":[79],"To":[80],"cope":[81],"with":[82],"this":[83],"challenge,":[84],"we":[85],"propose":[86],"novel":[88],"approach":[89],"uses":[93],"an":[94],"implicit":[95,111],"estimate":[96,112],"actions":[99],"guide":[101],"learning.":[105],"We":[106],"demonstrate":[107],"that":[108,130],"given":[109],"actions,":[115],"can":[118],"in":[122,141],"relatively":[124],"stationary":[125],"environment.":[126],"Extensive":[127],"experiments":[128],"show":[129],"our":[131],"method":[132],"significantly":[133],"alleviates":[134],"non-stationarity":[136],"outperforms":[138],"state-of-the-art":[140],"terms":[142],"both":[144],"convergence":[145],"speed":[146],"performance.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}