{"id":"W4402210774","doi":"10.1007/978-3-031-70903-6_16","title":"How to Better Fit Reinforcement Learning for Pentesting: A New Hierarchical Approach","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Machine learning","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":[0.001163261,0.0008940043,0.001298527,0.0004691318,0.000549707,0.001165271,0.002269373,0.001461049,0.01110468],"category_scores_gemma":[0.005796945,0.0005665017,0.001046027,0.0005797076,0.0008497374,0.003304671,0.002090783,0.002950695,0.001815684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009387751,"about_ca_system_score_gemma":0.001574231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006277741,"about_ca_topic_score_gemma":0.009621477,"domain_scores_codex":[0.9991721,0.0002584002,0.00005316956,0.0002027531,0.0001934326,0.0001202713],"domain_scores_gemma":[0.9985228,0.0006218316,0.00008942576,0.0004160154,0.0002414848,0.0001083853],"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":[0.0001606725,0.0002178798,0.0008426856,0.0002436663,0.0001111747,0.0001103398,0.0001701271,0.519734,0.005465424,0.07217532,0.009331523,0.3914372],"study_design_scores_gemma":[0.00001636647,0.00003810371,0.00007766568,0.00001709193,0.00001633211,0.00002155037,0.00001737659,0.9588696,0.0009297059,0.03763829,0.002347161,0.00001078659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004678296,0.0002340785,0.9903931,0.0003235842,0.00008000049,0.00004026554,0.00004070655,0.0009088932,0.003301052],"genre_scores_gemma":[0.1875816,0.0002729496,0.8032508,0.0003949386,0.0000835305,0.0001455653,0.0001512249,0.0006647824,0.00745462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01110468,"threshold_uncertainty_score":0.03714883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03748018830220856,"score_gpt":0.2653844963416743,"score_spread":0.2279043080394657,"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."}}