{"id":"W3121012756","doi":"10.1109/iv47402.2020.9304647","title":"Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Toyota Foundation","keywords":"Jerk; Reinforcement learning; Acceleration; Control theory (sociology); Collision avoidance; Computer science; Motion control; Control (management); Trajectory; Function (biology); Minification; Penalty method; Artificial intelligence; Engineering; Collision; Robot; Mathematics; Mathematical optimization; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.00005033046,0.0001230873,0.0001369843,0.00004248542,0.00006155763,0.00003779855,0.00008430263,0.00002393193,0.000285645],"category_scores_gemma":[0.00001253621,0.0001173855,0.00004988549,0.000116021,0.000005838787,0.00006551432,0.00003990714,0.000131092,0.0001259204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003639844,"about_ca_system_score_gemma":0.000003457962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008558501,"about_ca_topic_score_gemma":0.000002267732,"domain_scores_codex":[0.9993342,0.000007591019,0.0001537929,0.0001355968,0.0001396635,0.0002291656],"domain_scores_gemma":[0.9997857,0.00001657162,0.00001500543,0.00008784235,0.000008643618,0.00008622625],"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":[0.000003591771,0.000002962834,0.00002580422,0.00003149711,0.00004724698,0.000007731668,0.0003384664,0.9803207,0.002521444,0.0008524999,0.0002904024,0.01555763],"study_design_scores_gemma":[0.0003184024,0.00003342786,0.000131912,0.00001272287,0.00001717825,4.29078e-7,0.0001805754,0.9645348,0.0004735972,0.000002885845,0.03414499,0.0001490584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1692566,0.0002431525,0.7007576,0.000909773,0.0005276388,0.0003612418,2.272671e-7,0.002348061,0.1255957],"genre_scores_gemma":[0.998272,0.00002558851,0.0008419362,0.0004785639,0.000116445,0.000004139252,0.000002412927,0.00002382371,0.0002350972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8290154,"threshold_uncertainty_score":0.4786842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01463287867269203,"score_gpt":0.2037364873346368,"score_spread":0.1891036086619448,"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."}}