{"id":"W7134938218","doi":"10.1109/aiot66900.2025.00136","title":"A Comparative Evaluation of Teacher-Guided Reinforcement Learning Techniques for Autonomous Cyber Operations","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Automation; Control (management); Key (lock); Action (physics)","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"],"consensus_categories":[],"category_scores_codex":[0.004551079,0.0004602127,0.0007560403,0.0005925638,0.0007096913,0.000444495,0.001048572,0.0002540876,0.0004567074],"category_scores_gemma":[0.0008726728,0.0004688945,0.0002750894,0.001016043,0.0002194168,0.0008227305,0.0005640328,0.0004803988,0.00002738742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008264834,"about_ca_system_score_gemma":0.002106766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002082036,"about_ca_topic_score_gemma":0.00003553659,"domain_scores_codex":[0.9950699,0.0006508441,0.001777302,0.0007791733,0.001140069,0.0005827626],"domain_scores_gemma":[0.9949262,0.0003366702,0.0005447236,0.0009540207,0.00313867,0.00009971129],"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":[0.00001849997,0.00009349019,0.0001070548,0.00008804887,0.0002561763,1.346286e-7,0.003246353,0.8736769,0.001294279,0.1085432,0.001877145,0.01079871],"study_design_scores_gemma":[0.001301906,0.0006777243,0.0001775573,0.0003143721,0.000371648,0.000001434895,0.0005551659,0.9429153,0.04416746,0.000308151,0.008819673,0.0003896695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00113674,0.0001507762,0.8761111,0.0007678658,0.0004714869,0.004148635,0.000001160098,0.000228249,0.1169839],"genre_scores_gemma":[0.8266762,0.00002873222,0.1245355,0.0002045213,0.00005984334,0.000629274,0.00004159164,0.00001693978,0.04780736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8255395,"threshold_uncertainty_score":0.9997763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08454914817489433,"score_gpt":0.3828440244483338,"score_spread":0.2982948762734394,"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."}}