{"id":"https://openalex.org/W4406612200","doi":"https://doi.org/10.1109/wsc63780.2024.10838812","title":"Offline Reinforcement Learning for Autonomous Cyber Defense Agents","display_name":"Offline Reinforcement Learning for Autonomous Cyber Defense Agents","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406612200","doi":"https://doi.org/10.1109/wsc63780.2024.10838812"},"language":"en","primary_location":{"id":"doi:10.1109/wsc63780.2024.10838812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064061424","display_name":"Alexander Wei","orcid":"https://orcid.org/0000-0002-4295-5361"},"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":"Alexander Wei","raw_affiliation_strings":["Army Cyber Institute, United States Military Academy,West Point,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, United States Military Academy,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042696851","display_name":"David Bierbrauer","orcid":"https://orcid.org/0000-0002-4329-8551"},"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":"David Bierbrauer","raw_affiliation_strings":["Army Cyber Institute, United States Military Academy,West Point,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, United States Military Academy,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095953909","display_name":"Emily A. Nack","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":"Emily Nack","raw_affiliation_strings":["Army Cyber Institute, United States Military Academy,West Point,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, United States Military Academy,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076641949","display_name":"John V. Pavlik","orcid":"https://orcid.org/0000-0002-9899-0940"},"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":"John Pavlik","raw_affiliation_strings":["Army Cyber Institute, United States Military Academy,West Point,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, United States Military Academy,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 Bastian","raw_affiliation_strings":["Army Cyber Institute, United States Military Academy,West Point,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, United States Military Academy,West Point,NY,USA","institution_ids":["https://openalex.org/I192545095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192545095"],"apc_list":null,"apc_paid":null,"fwci":1.5673,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84032232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1978","last_page":"1989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9706000089645386,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9706000089645386,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9332000017166138,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.932200014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.785160481929779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6530461311340332},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4334336221218109},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.42569872736930847},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4148690104484558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3357163667678833}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.785160481929779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6530461311340332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4334336221218109},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.42569872736930847},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4148690104484558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357163667678833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wsc63780.2024.10838812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2032100464","https://openalex.org/W2565020460","https://openalex.org/W2612365756","https://openalex.org/W2910711617","https://openalex.org/W3167041328","https://openalex.org/W4224233018","https://openalex.org/W4322627146","https://openalex.org/W4380318870","https://openalex.org/W4380359312","https://openalex.org/W4390970201"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Advanced":[0],"Persistent":[1],"Threats":[2],"(APTs)":[3],"present":[4],"an":[5,48,98,106],"evolving":[6],"challenge":[7],"in":[8,122],"cybersecurity":[9],"through":[10,79],"increasingly":[11],"sophisticated":[12],"behavior.":[13],"Cybersecurity":[14],"Operations":[15],"Centers":[16],"(CSOCs)":[17],"rely":[18],"on":[19],"standard":[20],"playbooks":[21,50],"to":[22,24,54,84,103,139],"respond":[23],"myriad":[25],"cyber":[26,76],"threats;":[27],"however,":[28],"such":[29],"methods":[30],"quickly":[31],"become":[32],"outdated,":[33],"leaving":[34],"sensitive":[35],"data":[36,101],"at":[37],"significant":[38],"risk":[39],"for":[40,61,141],"theft":[41],"and":[42,56,67,111],"exploitation.":[43],"To":[44],"provide":[45],"CSOCs":[46],"with":[47,63],"advantage,":[49],"capable":[51],"of":[52],"adapting":[53],"threats":[55],"environments":[57],"must":[58,136],"be":[59],"developed":[60],"use":[62],"modern":[64],"security":[65],"orchestration":[66],"automation":[68],"tools.":[69],"Our":[70],"methodology":[71],"proposed":[72],"herein":[73],"trains":[74],"autonomous":[75],"defense":[77],"agents":[78],"offline":[80,109],"reinforcement":[81],"learning":[82],"(RL)":[83],"address":[85],"this":[86],"need.":[87],"Using":[88],"the":[89,134],"scalable,":[90],"tailorable":[91],"Cyber":[92],"Virtual":[93],"Assured":[94],"Network,":[95],"we":[96,119],"simulate":[97],"APT":[99],"conducting":[100],"exfiltration":[102,124],"then":[104],"train":[105],"agent":[107,135],"using":[108],"RL":[110],"compare":[112],"performance":[113],"against":[114],"a":[115],"myopic":[116],"policy.":[117],"Initially,":[118],"see":[120],"improvements":[121],"preventing":[123],"while":[125],"ensuring":[126],"authorized":[127],"user":[128],"access,":[129],"but":[130],"it":[131],"is":[132],"clear":[133],"periodically":[137],"retrain":[138],"account":[140],"changing":[142],"adversarial":[143],"behaviors.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
