{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002134942,0.0007543736,0.0008929892,0.000575744,0.00186528,0.001112213,0.002015864,0.0004408489,0.0005078159],"category_scores_gemma":[0.0007964221,0.0008107846,0.0005768199,0.00142675,0.0002169913,0.0009165641,0.001499227,0.001371394,0.0001572189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005028068,"about_ca_system_score_gemma":0.0008679461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001873284,"about_ca_topic_score_gemma":0.00007933166,"domain_scores_codex":[0.9944015,0.0003670643,0.001188469,0.001816175,0.0005323372,0.001694436],"domain_scores_gemma":[0.9965079,0.001205935,0.0004774569,0.001108385,0.000377244,0.0003231073],"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":[0.0001564806,0.0000820603,0.0004754694,0.000115851,0.0002002876,0.00002681116,0.008388527,0.4099202,0.0000557739,0.2205588,0.0003578595,0.3596619],"study_design_scores_gemma":[0.003818577,0.0002061928,0.0003887267,0.000180287,0.0001624222,0.00001779135,0.001336456,0.8977496,0.0002173383,0.003480207,0.09166455,0.0007778192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002543319,0.0007193373,0.9036448,0.00242143,0.004783907,0.001171277,0.000001028517,0.0006631352,0.0840518],"genre_scores_gemma":[0.7552865,0.00003439793,0.1963822,0.001148222,0.0004167241,0.0001499044,0.000009722171,0.00006846689,0.0465039],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7527432,"threshold_uncertainty_score":0.9999247,"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."}}