{"id":"W4401047823","doi":"10.1145/3680468","title":"Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Evolutionary algorithm; Population; Evolutionary robotics; Domain knowledge","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001637046,0.0007168108,0.0006920752,0.0006685937,0.0002422007,0.0004855109,0.001119367,0.0008395492,0.001291701],"category_scores_gemma":[0.006567692,0.000352607,0.0004245105,0.0003471333,0.0009840295,0.0006239649,0.000786807,0.001126905,0.0001747323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008135081,"about_ca_system_score_gemma":0.001091908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052337,"about_ca_topic_score_gemma":0.002577135,"domain_scores_codex":[0.999171,0.0004387732,0.00003022921,0.0000804874,0.0002047194,0.00007472796],"domain_scores_gemma":[0.9974434,0.001893289,0.0001888534,0.0001535739,0.0002379085,0.00008300968],"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":[0.00002156109,0.00003411132,0.000538301,0.0000211181,0.00001628864,0.00003410996,0.00002531409,0.9785776,0.0007393286,0.002957237,0.0001668058,0.01686815],"study_design_scores_gemma":[0.000007820371,0.0000190712,0.00006138723,0.00000340906,0.000002398907,0.000006319471,0.000003379848,0.99793,0.000213886,0.001605495,0.000145173,0.000001616925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09699502,0.000549534,0.8964621,0.0004046769,0.00004569467,0.0001105875,0.00003960859,0.0009868313,0.004405802],"genre_scores_gemma":[0.8828777,0.0001349245,0.115334,0.0001289129,0.00001663459,0.0001587965,0.00006120846,0.00006734762,0.001220411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003052337,"threshold_uncertainty_score":0.008657634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1268529696119229,"score_gpt":0.3405972594143513,"score_spread":0.2137442898024285,"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."}}