{"id":"https://openalex.org/W7117875630","doi":"https://doi.org/10.1109/milcom64451.2025.11310735","title":"Multi-Agent Deep Reinforcement Learning for Cyber Conflict Simulation and Experimentation","display_name":"Multi-Agent Deep Reinforcement Learning for Cyber Conflict Simulation and Experimentation","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W7117875630","doi":"https://doi.org/10.1109/milcom64451.2025.11310735"},"language":null,"primary_location":{"id":"doi:10.1109/milcom64451.2025.11310735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom64451.2025.11310735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2025 - 2025 IEEE Military Communications Conference (MILCOM)","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/A5121697165","display_name":"Matthew L. Corbett","orcid":null},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew L. Corbett","raw_affiliation_strings":["United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA"],"affiliations":[{"raw_affiliation_string":"United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103562385","display_name":"J. S. MURPHY","orcid":null},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared M. Murphy","raw_affiliation_strings":["United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA"],"affiliations":[{"raw_affiliation_string":"United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032194186","display_name":"Nathaniel D. Bastian","orcid":"https://orcid.org/0000-0001-9957-2778"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel D. Bastian","raw_affiliation_strings":["United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA"],"affiliations":[{"raw_affiliation_string":"United States Military Academy,Department of Electrical Engineering &#x0026; Computer Science,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121697165"],"corresponding_institution_ids":["https://openalex.org/I192545095"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82020219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1486","last_page":"1493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11219999939203262,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11219999939203262,"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/T10734","display_name":"Information and Cyber Security","score":0.10779999941587448,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.08049999922513962,"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/cyberspace","display_name":"Cyberspace","score":0.9463000297546387},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.8693000078201294},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.595300018787384},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5878999829292297},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5691999793052673},{"id":"https://openalex.org/keywords/cyber-attack","display_name":"Cyber-attack","score":0.4708999991416931},{"id":"https://openalex.org/keywords/stalemate","display_name":"Stalemate","score":0.38109999895095825},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.352400004863739},{"id":"https://openalex.org/keywords/cyber-physical-system","display_name":"Cyber-physical system","score":0.3424000144004822}],"concepts":[{"id":"https://openalex.org/C2781241145","wikidata":"https://www.wikidata.org/wiki/Q204606","display_name":"Cyberspace","level":3,"score":0.9463000297546387},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.8693000078201294},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.565500020980835},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C201307755","wikidata":"https://www.wikidata.org/wiki/Q4071928","display_name":"Cyber-attack","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C109913982","wikidata":"https://www.wikidata.org/wiki/Q208330","display_name":"Stalemate","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.34470000863075256},{"id":"https://openalex.org/C179768478","wikidata":"https://www.wikidata.org/wiki/Q1120057","display_name":"Cyber-physical system","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C171769113","wikidata":"https://www.wikidata.org/wiki/Q849340","display_name":"Cyberwarfare","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C127627568","wikidata":"https://www.wikidata.org/wiki/Q1639361","display_name":"Sociotechnical system","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C167343916","wikidata":"https://www.wikidata.org/wiki/Q6888384","display_name":"Modeling and simulation","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C100339178","wikidata":"https://www.wikidata.org/wiki/Q2548752","display_name":"Collective behavior","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom64451.2025.11310735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom64451.2025.11310735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2025 - 2025 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5076143741607666,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2050282514","https://openalex.org/W2465600334","https://openalex.org/W2625575095","https://openalex.org/W2902907165","https://openalex.org/W2952298682","https://openalex.org/W3107852229","https://openalex.org/W3139151242","https://openalex.org/W4214717370","https://openalex.org/W4231149792","https://openalex.org/W4254547512","https://openalex.org/W4284965199","https://openalex.org/W4295027442","https://openalex.org/W4362704894","https://openalex.org/W4365518811","https://openalex.org/W4389455162","https://openalex.org/W4396510479","https://openalex.org/W4399479546","https://openalex.org/W4399728997","https://openalex.org/W4401361149","https://openalex.org/W4406371502","https://openalex.org/W4406612200","https://openalex.org/W4407944619","https://openalex.org/W4416266169"],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"and":[1,7,37,55,73,80,88,107,129],"simulation":[2,56],"of":[3,9,78,109],"cyberspace":[4,28,69,134,141],"allows":[5,17],"experimentation":[6],"prediction":[8],"complex":[10,115,138],"cyber":[11,22,35,82,116,127],"systems.":[12],"Currently,":[13],"no":[14],"such":[15],"technique":[16,123],"for":[18,49,58],"modeling":[19,54],"or":[20,32],"simulating":[21,110],"conflict":[23],"between":[24],"two":[25],"learning,":[26],"capable":[27,68],"actors":[29],"with":[30,66],"equal":[31,34],"nearly":[33],"offensive":[36,79],"defensive":[38,81],"capabilities.":[39],"Our":[40],"work":[41],"builds":[42],"upon":[43],"existing":[44],"research":[45,119],"in":[46,113,140],"reinforcement":[47],"learning":[48],"cybersecurity":[50],"to":[51,84,124,136],"develop":[52],"a":[53,62,76,98,114],"platform":[57],"future":[59],"experimentation.":[60],"Using":[61],"customized":[63],"training":[64],"environment":[65],"symmetrically":[67],"competitors,":[70],"we":[71],"train":[72],"heuristically":[74],"verify":[75],"set":[77],"agents":[83,96],"achieve":[85,97],"optimal":[86],"individual":[87],"team":[89],"rewards.":[90],"We":[91],"then":[92],"validate":[93],"that":[94],"these":[95],"stalemate":[99],"when":[100],"competing":[101],"against":[102],"themselves,":[103],"proving":[104],"their":[105],"stability":[106],"capability":[108],"symmetrical":[111],"capabilities":[112],"system.":[117],"Future":[118],"can":[120],"exploit":[121],"this":[122],"model":[125],"arbitrary":[126],"environments":[128],"actions,":[130],"utilizing":[131],"highly":[132],"trained":[133],"operators":[135],"predict":[137],"outcomes":[139],"conflict.":[142]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-01T00:00:00"}
