{"id":"W7127450737","doi":"10.1109/ccece64018.2025.11364511","title":"Double Deep Q-Learning for Autonomous Cyber Defense Agent Training","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Training (meteorology); Multi-agent system; Intelligent agent; Autonomous agent; Training set","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001514965,0.000819004,0.0007281049,0.0003578484,0.0003556008,0.000536783,0.001515424,0.001218706,0.004777024],"category_scores_gemma":[0.003490223,0.0004924999,0.0003390027,0.0002981497,0.0007851124,0.0009242108,0.001461801,0.002013128,0.0009032683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008212912,"about_ca_system_score_gemma":0.001550436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004148477,"about_ca_topic_score_gemma":0.005405413,"domain_scores_codex":[0.9995503,0.0001473408,0.00001893869,0.0001007807,0.00008622497,0.00009637602],"domain_scores_gemma":[0.9987454,0.0007017939,0.0000739129,0.0001353523,0.0002397401,0.0001037227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001798631,0.0001424079,0.001372156,0.00008572713,0.00004501775,0.00005244604,0.00004818551,0.8565931,0.001993118,0.007892675,0.004393652,0.1272016],"study_design_scores_gemma":[0.000008866332,0.00002681768,0.00004761412,0.000003330759,0.00000198301,0.00000441685,0.000002992808,0.9971679,0.0003169204,0.002073164,0.0003443657,0.000001707371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03846824,0.0006158999,0.9526964,0.0005904482,0.000158663,0.00009975376,0.0001266233,0.002118105,0.005125852],"genre_scores_gemma":[0.8217981,0.0001800643,0.1697877,0.0006753788,0.00007385514,0.0001878472,0.0003980584,0.0001759717,0.006722879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004777024,"threshold_uncertainty_score":0.01598072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222072242703986,"score_gpt":0.2988361695255839,"score_spread":0.266615447098544,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}