{"id":"W2945137235","doi":"10.1109/itsc.2019.8916781","title":"Longitudinal Dynamic versus Kinematic Models for Car-Following Control Using Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Acceleration; Kinematics; Vehicle dynamics; Cruise control; Control theory (sociology); Reinforcement learning; Computer science; Controller (irrigation); Dynamics (music); Control engineering; Engineering; Control (management); Artificial intelligence; Automotive engineering; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002858617,0.0005246922,0.0007714829,0.000211933,0.00009941059,0.0001484019,0.0003208939,0.0002274112,0.0000441576],"category_scores_gemma":[0.00002799133,0.000534427,0.0005403276,0.00006550112,0.00001136528,0.0001437682,0.0002360589,0.0004766182,0.00002002771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005358392,"about_ca_system_score_gemma":0.00004453898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007944593,"about_ca_topic_score_gemma":0.00008254711,"domain_scores_codex":[0.9979578,0.00002272293,0.0005901631,0.0004869358,0.0003314294,0.0006109476],"domain_scores_gemma":[0.9990631,0.0001667001,0.0001216664,0.0004973646,0.00005702903,0.00009419162],"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":[0.00008405671,0.00000922577,0.000008878976,0.001331549,0.0009632832,0.000006076054,0.0001330315,0.9949157,0.0001157301,0.0005898824,0.00002967168,0.001812959],"study_design_scores_gemma":[0.004345958,0.00006450704,0.00003374097,0.0002452886,0.0008283756,7.624594e-7,0.0001419793,0.9934539,0.000003904521,0.0001683935,0.0001401565,0.0005729969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01907334,0.0007317069,0.9689733,0.00002987133,0.003677328,0.002191457,0.000004239351,0.0007348239,0.004583949],"genre_scores_gemma":[0.9931055,0.00004206675,0.005632645,0.00001559278,0.0001131304,0.0002779143,0.00008005952,0.0001110003,0.0006220403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9740322,"threshold_uncertainty_score":0.9997107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02282628764486168,"score_gpt":0.247897770208289,"score_spread":0.2250714825634273,"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."}}