{"id":"W2981402159","doi":"10.1109/tiv.2020.3012947","title":"Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Traffic control and management","field":"Engineering","cited_by":224,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Model predictive control; Cruise control; Generalization; Benchmark (surveying); Computer science; Range (aeronautics); Control theory (sociology); Control (management); Artificial intelligence; Engineering; Mathematics","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":[0.0000781889,0.0001966985,0.0003601411,0.00008145125,0.00009394893,0.0000177964,0.00008690255,0.00006630579,0.00002130267],"category_scores_gemma":[0.000006418234,0.000196815,0.0001316536,0.00007069553,0.00005070061,0.00007684783,0.000001038939,0.0002115694,0.000005443216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004783462,"about_ca_system_score_gemma":0.000009740995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004774352,"about_ca_topic_score_gemma":0.00001306344,"domain_scores_codex":[0.9989929,0.00002374893,0.0003931261,0.0002070254,0.000164827,0.0002183771],"domain_scores_gemma":[0.9994646,0.0001940789,0.00006206306,0.00008223108,0.0000729902,0.0001239946],"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":[0.0009833772,0.00006349329,0.00001563062,0.00008859214,0.0003801083,3.951149e-7,0.001456586,0.9545872,0.002035472,0.000256783,0.00005025689,0.04008211],"study_design_scores_gemma":[0.001830147,0.0008810281,0.00002029553,0.00002944623,0.0002385853,2.24159e-7,0.0009124122,0.9834979,0.01205731,0.00004523788,0.0003220115,0.0001654567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004290346,0.0003136529,0.9936877,0.0001611169,0.0001201048,0.0009304587,0.0000401037,0.0002325396,0.0002240052],"genre_scores_gemma":[0.9988576,0.0001233667,0.000577785,0.000103498,0.00003079652,0.0002382739,0.000002116684,0.00002977397,0.00003676795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9945673,"threshold_uncertainty_score":0.8025883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02467582414128084,"score_gpt":0.2510950127307898,"score_spread":0.2264191885895089,"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."}}