{"id":"W3154647937","doi":"10.1117/12.2585173","title":"Autonomous network cyber offence strategy through deep reinforcement learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Artificial intelligence; Domain (mathematical analysis); Computer security","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":[0.0008966078,0.0006895757,0.000539476,0.0003328485,0.0002270665,0.0006168969,0.0009369971,0.0006194247,0.0009668768],"category_scores_gemma":[0.002664653,0.0002789773,0.0002620079,0.0001559178,0.0006451114,0.0006179284,0.0006988618,0.00106833,0.0001831455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000901357,"about_ca_system_score_gemma":0.0009863977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006619612,"about_ca_topic_score_gemma":0.005557676,"domain_scores_codex":[0.9997699,0.00006466285,0.00001127569,0.00005537822,0.00004819898,0.00005068674],"domain_scores_gemma":[0.9988528,0.0006124459,0.0001749851,0.00007407794,0.0002072908,0.0000783034],"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":[0.00004791066,0.00009391963,0.00120281,0.00002241678,0.00002311143,0.00003375423,0.00003899673,0.9656362,0.001415598,0.00165199,0.0004114587,0.02942185],"study_design_scores_gemma":[0.000003650099,0.0000213689,0.00005155461,0.000001771106,0.00000206389,0.000002772541,0.000002813754,0.9992866,0.000222981,0.0003403407,0.0000627603,0.000001300793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2913173,0.0004236365,0.6971427,0.0006418425,0.000086082,0.0001615613,0.00006449864,0.001455472,0.00870705],"genre_scores_gemma":[0.9721562,0.00004569881,0.02620633,0.00008646625,0.000007866346,0.00004469839,0.00003787036,0.00002084025,0.001393968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006619612,"threshold_uncertainty_score":0.01316214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01811257081527174,"score_gpt":0.2637725179767449,"score_spread":0.2456599471614732,"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."}}