{"id":"https://openalex.org/W4385235640","doi":"https://doi.org/10.1109/med59994.2023.10185760","title":"Modifying Neural Networks in Adversarial Agents of Multi-agent Reinforcement Learning Systems","display_name":"Modifying Neural Networks in Adversarial Agents of Multi-agent Reinforcement Learning Systems","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4385235640","doi":"https://doi.org/10.1109/med59994.2023.10185760"},"language":"en","primary_location":{"id":"doi:10.1109/med59994.2023.10185760","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/med59994.2023.10185760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Mediterranean Conference on Control and Automation (MED)","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/A5039849395","display_name":"Neshat Elhami Fard","orcid":"https://orcid.org/0000-0002-7093-2693"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Neshat Elhami Fard","raw_affiliation_strings":["Concordia University,Department of Electrical and Computer Engineering,Montreal,Canada,QC H3G 1M8"],"affiliations":[{"raw_affiliation_string":"Concordia University,Department of Electrical and Computer Engineering,Montreal,Canada,QC H3G 1M8","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064990097","display_name":"Rastko R. \u0160elmi\u0107","orcid":"https://orcid.org/0000-0001-9345-8077"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rastko R. Selmic","raw_affiliation_strings":["Concordia University,Department of Electrical and Computer Engineering,Montreal,Canada,QC H3G 1M8"],"affiliations":[{"raw_affiliation_string":"Concordia University,Department of Electrical and Computer Engineering,Montreal,Canada,QC H3G 1M8","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039849395"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09632929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"824","last_page":"829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.9664000272750854,"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"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.9664000272750854,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9187999963760376,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8043167591094971},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7873053550720215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407397627830505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5679726600646973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5090746283531189},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4953700304031372}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8043167591094971},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7873053550720215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407397627830505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5679726600646973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090746283531189},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4953700304031372}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/med59994.2023.10185760","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/med59994.2023.10185760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Mediterranean Conference on Control and Automation (MED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1974515126","https://openalex.org/W2017388686","https://openalex.org/W2046376809","https://openalex.org/W2119959427","https://openalex.org/W2153966110","https://openalex.org/W2533465884","https://openalex.org/W2617547828","https://openalex.org/W2750126382","https://openalex.org/W2788115019","https://openalex.org/W2894976951","https://openalex.org/W3017317138","https://openalex.org/W3033491900","https://openalex.org/W3118412160","https://openalex.org/W3186333353","https://openalex.org/W3199602519","https://openalex.org/W4280563754","https://openalex.org/W4282944995","https://openalex.org/W4287330971","https://openalex.org/W4289829023","https://openalex.org/W4297825308","https://openalex.org/W4299802797","https://openalex.org/W4315488874","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6755069753","https://openalex.org/W6791040878"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"This":[0,120],"paper":[1],"proposes":[2],"a":[3,13,75,82,87,94],"method":[4,23],"to":[5,34,64,110,132],"reduce":[6,44],"the":[7,25,29,36,45,51,57,66,111,118,124,127,133,143],"malicious":[8,46,67],"agent\u2019s":[9,68],"negative":[10],"effects":[11,49],"on":[12,50],"multi-agent":[14],"reinforcement":[15],"learning":[16],"(MARL)":[17],"system,":[18,31],"including":[19],"actor-critic":[20],"architecture.":[21],"The":[22,136],"achieves":[24],"overall":[26],"goal":[27],"of":[28,39,113,126],"MARL":[30,53],"which":[32],"is":[33,60,108],"increase":[35],"cumulative":[37],"reward":[38],"all":[40],"individual":[41],"agents":[42],"and":[43,142],"agents\u2019":[47],"harmful":[48],"entire":[52],"system.":[54],"Assuming":[55],"that":[56,81,104],"adverse":[58],"agent":[59],"detectable,":[61],"we":[62,78],"propose":[63],"change":[65],"neural":[69],"network":[70],"(NN)":[71],"structure.":[72],"By":[73],"leveraging":[74],"comparative":[76],"methodology,":[77],"have":[79,138],"demonstrated":[80],"specific":[83],"NN":[84],"architecture":[85],"using":[86],"linear":[88],"activation":[89,96,115,134],"function":[90,97,129],"surpasses":[91],"another":[92],"utilizing":[93],"sigmoid":[95],"in":[98],"minimizing":[99],"loss.":[100],"Our":[101],"analysis":[102],"indicates":[103],"this":[105],"performance":[106],"differential":[107],"attributable":[109],"utilization":[112],"distinct":[114],"functions":[116],"within":[117],"models.":[119],"approach":[121],"involves":[122],"calculating":[123],"gradient":[125],"loss":[128],"with":[130],"respect":[131],"function.":[135],"claims":[137],"been":[139],"proven":[140],"theoretically,":[141],"simulation":[144],"confirms":[145],"theoretical":[146],"findings.":[147]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}