{"id":"W2911324515","doi":"10.1007/978-3-030-30281-8_20","title":"WiseMove: A Framework to Investigate Safe Deep Reinforcement Learning for Autonomous Driving","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Modular design; Scalability; Context (archaeology); Software; Motion planning; Architecture; Deep learning","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":[0.0004490153,0.0004757779,0.0005164969,0.0005543705,0.0002174796,0.0001021751,0.001012928,0.000672167,0.00003843587],"category_scores_gemma":[0.0001788145,0.000498708,0.0001091496,0.0002703479,0.0003036556,0.0001453215,0.0004308526,0.001373157,0.0001089407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005069429,"about_ca_system_score_gemma":0.000223114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003503744,"about_ca_topic_score_gemma":0.0000282377,"domain_scores_codex":[0.9977605,0.000008014936,0.0004626722,0.0007695269,0.0002903146,0.0007089966],"domain_scores_gemma":[0.9985515,0.0004296878,0.0001123722,0.000677494,0.00007457353,0.0001543242],"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":[0.000003545955,0.000001815311,0.00006600522,0.00005179597,0.00001474109,0.000006050213,0.0004937096,0.8070879,0.0001103282,0.006290381,0.000007156948,0.1858666],"study_design_scores_gemma":[0.000146107,0.0001623247,0.0001067757,0.0005116554,0.00001219899,0.00001183338,3.558414e-7,0.9457524,0.001296824,0.04390089,0.007476886,0.0006217865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000696612,0.0002277432,0.9933928,0.0003858287,0.001162555,0.0007546589,0.000001133346,0.0005721449,0.002806548],"genre_scores_gemma":[0.7105548,0.00003237037,0.2870581,0.001077114,0.0002869655,0.00003423835,0.000008520724,0.00009913581,0.0008487464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7098582,"threshold_uncertainty_score":0.9997464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00858529657000148,"score_gpt":0.2190842659755918,"score_spread":0.2104989694055903,"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."}}