{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002806376,0.001809857,0.0009676942,0.000558682,0.0003202329,0.000689582,0.002188347,0.001390974,0.001714366],"category_scores_gemma":[0.009854577,0.0005622521,0.000521069,0.0002700733,0.001046176,0.001451341,0.001243003,0.001993543,0.0002488607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001672229,"about_ca_system_score_gemma":0.001457647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007898838,"about_ca_topic_score_gemma":0.008502185,"domain_scores_codex":[0.9987512,0.0005082365,0.00009126327,0.0002489909,0.0002535701,0.000146673],"domain_scores_gemma":[0.9942499,0.004082301,0.0004890286,0.0002935634,0.0006118036,0.0002733562],"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":[0.0001431199,0.0001497266,0.001653363,0.00009539344,0.00003729037,0.00007187386,0.00003023454,0.9649999,0.001154064,0.0008268367,0.0003656353,0.03047255],"study_design_scores_gemma":[0.000008838352,0.00004214608,0.00008319124,0.000004482306,0.000002916971,0.000004929564,0.000003138587,0.9986274,0.0005558237,0.0006096035,0.00005507133,0.000002379416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3024873,0.001561535,0.6856557,0.0007101802,0.000131692,0.0002839697,0.0002593449,0.004356846,0.004553461],"genre_scores_gemma":[0.9527897,0.0001023553,0.04589372,0.0001763594,0.00001316395,0.0001181249,0.0001819073,0.0000697085,0.0006549141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007898838,"threshold_uncertainty_score":0.0157057,"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."}}