{"id":"W4384345629","doi":"10.1109/icse48619.2023.00155","title":"Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Fidelity; Artificial intelligence; High fidelity; Machine learning; Artificial neural network; Human–computer interaction","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006801116,0.0001112624,0.0001955352,0.0002000533,0.0001315855,0.00006710646,0.000415308,0.00004476786,0.00000120972],"category_scores_gemma":[0.002115265,0.00009710347,0.00004950989,0.0008014516,0.00001896358,0.0001456652,0.0002410219,0.00009628205,0.000008467405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004449152,"about_ca_system_score_gemma":0.00006558582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00030479,"about_ca_topic_score_gemma":0.000001220647,"domain_scores_codex":[0.998902,0.00003500606,0.0003040854,0.0002707951,0.0002075761,0.0002805992],"domain_scores_gemma":[0.9976932,0.001496757,0.0001667078,0.0003150507,0.0002841136,0.00004414668],"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":[0.0000548924,0.0002662689,0.03779523,0.001694403,0.0002284411,0.00005625916,0.003463312,0.5532023,0.006889086,0.09550369,0.09430547,0.2065406],"study_design_scores_gemma":[0.0001874558,0.0002952048,0.0008432054,0.0001704001,0.000004927162,0.00000709324,0.00004290137,0.9922115,0.00145465,0.004077012,0.000575146,0.0001305306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00912086,0.00002113388,0.9734991,0.00007542186,0.000178796,0.0003560991,9.033539e-7,0.01485789,0.001889811],"genre_scores_gemma":[0.6992723,0.000002160986,0.2980966,0.00003987282,0.0000552216,0.00007242565,0.000008334532,0.0000133186,0.002439737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6901515,"threshold_uncertainty_score":0.3959765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05353553344486145,"score_gpt":0.296018447556249,"score_spread":0.2424829141113875,"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."}}