{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001014196,0.0008009577,0.000682617,0.001265713,0.0003770011,0.002920819,0.004173579,0.0003467645,0.00001189371],"category_scores_gemma":[0.0005012696,0.0007334244,0.0002744673,0.0008642529,0.0003136346,0.0006133908,0.002939074,0.001820428,0.00008190775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004975828,"about_ca_system_score_gemma":0.0006945428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001099296,"about_ca_topic_score_gemma":0.000004048972,"domain_scores_codex":[0.9942064,0.00002694106,0.0006773497,0.002283471,0.001578723,0.00122713],"domain_scores_gemma":[0.996784,0.0007633448,0.0002954463,0.001411363,0.0002446358,0.0005011819],"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":[0.000005713317,0.00000641732,0.00001256309,0.0001106805,0.00002000057,0.00002465001,0.0008369508,0.8483432,0.00003791574,0.02451148,0.0002665191,0.1258239],"study_design_scores_gemma":[0.0002730063,0.0005006066,0.000007016437,0.0005330952,0.0000187254,0.00005324405,3.569446e-7,0.9327112,0.0001451947,0.02941278,0.03555447,0.0007903063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000004932402,0.000146039,0.9842208,0.006944062,0.00164662,0.001273062,8.698652e-7,0.0004031036,0.005360494],"genre_scores_gemma":[0.02029405,0.000008970966,0.9358998,0.002806545,0.001381735,0.00005228753,0.00001707196,0.00009793328,0.03944161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1250336,"threshold_uncertainty_score":0.9995117,"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."}}