{"id":"https://openalex.org/W4402261074","doi":"https://doi.org/10.23919/acc60939.2024.10644829","title":"Risk-Aware Distributed Multi-Agent Reinforcement Learning","display_name":"Risk-Aware Distributed Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402261074","doi":"https://doi.org/10.23919/acc60939.2024.10644829"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644829","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5018279576","display_name":"Abdullah Al Maruf","orcid":"https://orcid.org/0000-0001-5610-5483"},"institutions":[{"id":"https://openalex.org/I27825529","display_name":"California State University Los Angeles","ror":"https://ror.org/0294hxs80","country_code":"US","type":"education","lineage":["https://openalex.org/I27825529"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdullah Al Maruf","raw_affiliation_strings":["California State University,Department of Electrical and Computer Engineering,Los Angeles,CA,USA,90032"],"affiliations":[{"raw_affiliation_string":"California State University,Department of Electrical and Computer Engineering,Los Angeles,CA,USA,90032","institution_ids":["https://openalex.org/I27825529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018806127","display_name":"Luyao Niu","orcid":"https://orcid.org/0000-0001-8591-5522"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luyao Niu","raw_affiliation_strings":["University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"],"affiliations":[{"raw_affiliation_string":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052064870","display_name":"Bhaskar Ramasubramanian","orcid":"https://orcid.org/0000-0002-2166-7838"},"institutions":[{"id":"https://openalex.org/I52669646","display_name":"Western Washington University","ror":"https://ror.org/05wn7r715","country_code":"US","type":"education","lineage":["https://openalex.org/I52669646"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhaskar Ramasubramanian","raw_affiliation_strings":["Western Washington University,Electrical and Computer Engineering,Bellingham,WA,USA,98225"],"affiliations":[{"raw_affiliation_string":"Western Washington University,Electrical and Computer Engineering,Bellingham,WA,USA,98225","institution_ids":["https://openalex.org/I52669646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043078408","display_name":"Andrew M. Clark","orcid":"https://orcid.org/0000-0002-7906-8678"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Clark","raw_affiliation_strings":["Washington University in St. Louis,Electrical and Systems Engineering,St. Louis,MO,USA,63130"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis,Electrical and Systems Engineering,St. Louis,MO,USA,63130","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079723268","display_name":"Radha Poovendran","orcid":"https://orcid.org/0000-0003-0269-8097"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radha Poovendran","raw_affiliation_strings":["University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"],"affiliations":[{"raw_affiliation_string":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018279576"],"corresponding_institution_ids":["https://openalex.org/I27825529"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6634355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4012","last_page":"4019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9634000062942505,"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":0.8257315158843994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523320317268372},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43330153822898865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37042421102523804},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33824706077575684}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8257315158843994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523320317268372},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43330153822898865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37042421102523804},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33824706077575684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644829","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G8325461916","display_name":null,"funder_award_id":"FA9550-22-1-0054,FA9550-23-1-0208","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W580164506","https://openalex.org/W1825869920","https://openalex.org/W1918371733","https://openalex.org/W1965878388","https://openalex.org/W2019291268","https://openalex.org/W2088413745","https://openalex.org/W2096145798","https://openalex.org/W2098432798","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2139914196","https://openalex.org/W2145339207","https://openalex.org/W2266738696","https://openalex.org/W2411577903","https://openalex.org/W2617547828","https://openalex.org/W2901621510","https://openalex.org/W2909906617","https://openalex.org/W2962883549","https://openalex.org/W2963762747","https://openalex.org/W2989958156","https://openalex.org/W2991046523","https://openalex.org/W3111425826","https://openalex.org/W3120310250","https://openalex.org/W3124407081","https://openalex.org/W3130263801","https://openalex.org/W3157075202","https://openalex.org/W3215494060","https://openalex.org/W4210320318","https://openalex.org/W4210333964","https://openalex.org/W4221146569","https://openalex.org/W4230962939","https://openalex.org/W4235236481","https://openalex.org/W4299802797","https://openalex.org/W6617021176","https://openalex.org/W6637033378","https://openalex.org/W6738796088","https://openalex.org/W6766805167","https://openalex.org/W6790997415","https://openalex.org/W6810183012","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Autonomous":[0],"cyber":[1],"and":[2,10,29,105,130,151,175,189],"cyber-physical":[3],"systems":[4],"need":[5],"to":[6,20,65,79,96,110,116,134,178],"perform":[7],"decision-making,":[8],"learning,":[9],"control":[11],"in":[12,27,33,83,167],"unknown":[13,84],"environments.":[14],"Such":[15],"decision-making":[16,81],"can":[17],"be":[18],"sensitive":[19],"multiple":[21],"factors,":[22],"including":[23],"modeling":[24],"errors,":[25],"changes":[26],"costs,":[28],"impacts":[30],"of":[31,36,156,170,193],"events":[32],"the":[34,54,67,92,98,112,135,147,168,171,183,191],"tails":[35],"probability":[37],"distributions.":[38],"Although":[39],"multi-agent":[40],"reinforcement":[41],"learning":[42,48,87],"(MARL)":[43],"provides":[44],"a":[45,75,107,117,127,142,194],"framework":[46],"for":[47],"behaviors":[49],"through":[50,187],"repeated":[51],"interactions":[52],"with":[53],"environment":[55],"by":[56,86],"minimizing":[57],"an":[58],"average":[59],"cost,":[60],"it":[61,132],"is":[62,102],"not":[63],"adequate":[64],"overcome":[66,179],"above":[68],"challenges.":[69],"In":[70],"this":[71,124],"paper,":[72],"we":[73],"develop":[74],"distributed":[76,143],"MARL":[77,144],"approach":[78],"solve":[80],"problems":[82],"environments":[85],"risk-aware":[88],"actions.":[89],"We":[90,121,139,161,181],"use":[91],"conditional":[93],"value-at-risk":[94],"(CVaR)":[95],"define":[97],"cost":[99],"function":[100,114],"that":[101,123,131,153,165],"being":[103],"minimized,":[104],"introduce":[106],"Bellman":[108],"operator":[109,125],"characterize":[111],"value":[113,137,154,198],"associated":[115],"given":[118],"state-action":[119],"pair.":[120],"prove":[122],"satisfies":[126],"contraction":[128],"property,":[129],"converges":[133],"optimal":[136],"function.":[138],"then":[140],"propose":[141],"algorithm":[145,186],"called":[146],"CVaR":[148,172,184],"QD-Learning":[149,173,185],"algorithm,":[150,174],"establish":[152],"functions":[155,199],"individual":[157],"agents":[158],"reach":[159],"consensus.":[160,201],"identify":[162],"several":[163],"challenges":[164],"arise":[166],"implementation":[169],"present":[176],"solutions":[177],"these.":[180],"evaluate":[182],"simulations,":[188],"demonstrate":[190],"effect":[192],"risk":[195],"parameter":[196],"on":[197],"at":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}