{"id":"W6989067501","doi":"","title":"Aggressiveness-regulated Multi-agent Stress Testing of Autonomous Vehicles","year":2023,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Reinforcement learning; Accident (philosophy); Quality (philosophy); Reinforcement; Task (project management); Stress test","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":[0.002376889,0.0006642507,0.0004018379,0.000378913,0.0002607693,0.0005993433,0.001090882,0.0005444895,0.0006183583],"category_scores_gemma":[0.00746308,0.0002542364,0.0004056967,0.0001410859,0.0007866803,0.0005257411,0.0008627475,0.0007632948,0.00009183517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008437632,"about_ca_system_score_gemma":0.001067036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003351016,"about_ca_topic_score_gemma":0.002480787,"domain_scores_codex":[0.9990131,0.0005273938,0.00003604306,0.0001163451,0.0002048989,0.0001021035],"domain_scores_gemma":[0.9949121,0.003214201,0.0006308137,0.0003682254,0.0006366601,0.0002380316],"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":[0.00009237338,0.0001286687,0.002807199,0.00004875643,0.0000262485,0.00003858794,0.00006101997,0.9723341,0.002778805,0.002682179,0.0002533084,0.01874882],"study_design_scores_gemma":[0.000008216852,0.000127663,0.0004015583,0.000007516837,0.000003873767,0.000006626315,0.00001603896,0.9964145,0.001582952,0.001236979,0.0001902555,0.000003819307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6265119,0.000304868,0.3667168,0.0003214436,0.00006302753,0.0002155846,0.0001057901,0.0007525505,0.005007888],"genre_scores_gemma":[0.9723799,0.00005245175,0.02680499,0.00003234384,0.000006693193,0.00008787517,0.00006242965,0.00002553268,0.0005476609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003351016,"threshold_uncertainty_score":0.01257032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147286928116283,"score_gpt":0.20237416692376,"score_spread":0.1876454741121316,"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."}}