{"id":"https://openalex.org/W4417255477","doi":"https://doi.org/10.48550/arxiv.2506.08192","title":"Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms","display_name":"Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4417255477","doi":"https://doi.org/10.48550/arxiv.2506.08192"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.08192","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08192","pdf_url":"https://arxiv.org/pdf/2506.08192","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.08192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093557701","display_name":"Jared Claypoole","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claypoole, Jared","raw_affiliation_strings":["( Laboratory for Advanced Cybersecurity Research)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( Laboratory for Advanced Cybersecurity Research)","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheung, Steven","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheung, Steven","raw_affiliation_strings":["( Laboratory for Advanced Cybersecurity Research)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( Laboratory for Advanced Cybersecurity Research)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035466033","display_name":"Ashish Gehani","orcid":"https://orcid.org/0000-0002-3940-2467","observed_orcids":["https://orcid.org/0000-0002-3940-2467"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gehani, Ashish","raw_affiliation_strings":["( Laboratory for Advanced Cybersecurity Research)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( Laboratory for Advanced Cybersecurity Research)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085002486","display_name":"Vinod Yegneswaran","orcid":"https://orcid.org/0000-0003-0718-6605","observed_orcids":["https://orcid.org/0000-0003-0718-6605"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yegneswaran, Vinod","raw_affiliation_strings":["( Laboratory for Advanced Cybersecurity Research)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( Laboratory for Advanced Cybersecurity Research)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086766935","display_name":"Ahmad Ridley","orcid":"https://orcid.org/0009-0007-5577-5347","observed_orcids":["https://orcid.org/0009-0007-5577-5347"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ridley, Ahmad","raw_affiliation_strings":["( Laboratory for Advanced Cybersecurity Research)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( Laboratory for Advanced Cybersecurity Research)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.7875999808311462,"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":0.7875999808311462,"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/T10734","display_name":"Information and Cyber Security","score":0.15610000491142273,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01590000092983246,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning-agents","display_name":"deep reinforcement learning agents","score":0.7440000176429749},{"id":"https://openalex.org/keywords/cyber-defense","display_name":"cyber defense","score":0.8759999871253967},{"id":"https://openalex.org/keywords/event-tracking","display_name":"event tracking","score":0.38499999046325684},{"id":"https://openalex.org/keywords/simulation-realism","display_name":"simulation realism","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8614000082015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145000100135803},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C2779179475","wikidata":"https://www.wikidata.org/wiki/Q3545649","display_name":"Decoy","level":3,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38989999890327454},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C151913843","wikidata":"https://www.wikidata.org/wiki/Q3454555","display_name":"Dominance (genetics)","level":3,"score":0.26339998841285706}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.08192","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08192","pdf_url":"https://arxiv.org/pdf/2506.08192","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.08192","doi":"https://doi.org/10.48550/arxiv.2506.08192","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08192","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.08192","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08192","pdf_url":"https://arxiv.org/pdf/2506.08192","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417255477.pdf","grobid_xml":"https://content.openalex.org/works/W4417255477.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3007573367","https://openalex.org/W3137498832","https://openalex.org/W4281388209","https://openalex.org/W4310563139","https://openalex.org/W4323921952","https://openalex.org/W4386794596"],"related_works":["https://openalex.org/W7117879103","https://openalex.org/W7139992152","https://openalex.org/W7169607328","https://openalex.org/W7154014629","https://openalex.org/W4412081997","https://openalex.org/W7117875630","https://openalex.org/W4386159217","https://openalex.org/W4385692460","https://openalex.org/W7123603590","https://openalex.org/W4416084053"],"abstract_inverted_index":{"We":[0,37,163],"analyze":[1],"two":[2,120],"open":[3],"source":[4],"deep":[5],"reinforcement":[6],"learning":[7],"agents":[8,74],"submitted":[9,21],"to":[10,24,114,145,178,188],"the":[11,51,65,70,100,131,136,194,197,202],"CAGE":[12,203],"Challenge":[13,204],"2":[14],"cyber":[15],"defense":[16,71],"challenge,":[17],"where":[18],"each":[19,30,76],"competitor":[20],"an":[22,84],"agent":[23,45],"defend":[25],"a":[26,123,189],"simulated":[27],"network":[28],"against":[29],"of":[31,44,68,122,180,196,209],"several":[32],"provided":[33],"rules-based":[34],"attack":[35,73],"agents.":[36],"demonstrate":[38],"that":[39,95,153,174,182,201],"one":[40,118],"can":[41],"gain":[42],"interpretability":[43],"successes":[46],"and":[47,54,57,72,92,102,148,160,199],"failures":[48],"by":[49,58,135],"simplifying":[50],"complex":[52],"state":[53,133],"action":[55],"spaces":[56],"tracking":[59],"important":[60,81,155],"events,":[61],"shedding":[62],"light":[63],"on":[64],"fine-grained":[66],"behavior":[67],"both":[69],"in":[75,90,130],"experimental":[77],"scenario.":[78],"By":[79,127],"analyzing":[80],"events":[82,94],"within":[83,117],"evaluation":[85],"episode,":[86],"we":[87,140,192],"identify":[88],"patterns":[89],"infiltration":[91],"clearing":[93],"tell":[96],"us":[97],"how":[98,165],"well":[99],"attacker":[101],"defender":[103],"played":[104],"their":[105],"respective":[106],"roles;":[107],"for":[108,172],"example,":[109],"defenders":[110],"were":[111],"generally":[112],"able":[113],"clear":[115],"infiltrations":[116],"or":[119],"timesteps":[121],"host":[124],"being":[125],"exploited.":[126],"examining":[128],"transitions":[129],"environment's":[132],"caused":[134],"various":[137],"possible":[138],"actions,":[139],"determine":[141],"which":[142,149],"actions":[143,156],"tended":[144],"be":[146],"effective":[147],"did":[150],"not,":[151],"showing":[152],"certain":[154],"are":[157],"between":[158],"40%":[159],"99%":[161],"ineffective.":[162],"examine":[164],"decoy":[166],"services":[167],"affect":[168],"exploit":[169],"success,":[170],"concluding":[171],"instance":[173],"decoys":[175],"block":[176],"up":[177],"94%":[179],"exploits":[181],"would":[183],"directly":[184],"grant":[185],"privileged":[186],"access":[187],"host.":[190],"Finally,":[191],"discuss":[193],"realism":[195],"challenge":[198],"ways":[200],"4":[205],"has":[206],"addressed":[207],"some":[208],"our":[210],"concerns.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}