{"id":"W3024430428","doi":"10.48550/arxiv.1909.12967","title":"Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Traffic control and management","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Ontario Centres of Excellence","keywords":"Jerk; Reinforcement learning; Acceleration; Control theory (sociology); Computer science; Collision avoidance; Control (management); Function (biology); Penalty method; Engineering; Collision; Artificial intelligence; Mathematical optimization; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005815246,0.0005245671,0.0005113649,0.0002201823,0.00022072,0.000365206,0.0006756162,0.0004110991,0.0008871969],"category_scores_gemma":[0.001164608,0.0002683567,0.0003175811,0.0001515648,0.0004749089,0.0003915114,0.0005724683,0.0007763203,0.0001161169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006345405,"about_ca_system_score_gemma":0.0009673624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00830097,"about_ca_topic_score_gemma":0.007279605,"domain_scores_codex":[0.9998131,0.00004122675,0.000006832312,0.00004228713,0.00004726386,0.00004921296],"domain_scores_gemma":[0.9995753,0.0001669882,0.00008570799,0.00004474395,0.00008316545,0.00004407992],"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":[0.00003575437,0.00003263999,0.000551407,0.00001138354,0.00001337332,0.00002305541,0.00001457428,0.9828699,0.001619248,0.0009770087,0.0001862596,0.01366526],"study_design_scores_gemma":[0.000002779306,0.00001578595,0.00007185109,7.70843e-7,0.000001372646,0.000001853293,9.299578e-7,0.9993325,0.000276658,0.0002498236,0.00004447274,0.000001209761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2577714,0.0002491542,0.7336416,0.0002509352,0.00006807215,0.00005423371,0.00004810228,0.00142061,0.006495871],"genre_scores_gemma":[0.9861407,0.0000154895,0.01305719,0.00002751859,0.000004710382,0.0000140003,0.00001816119,0.0000119621,0.0007101888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00830097,"threshold_uncertainty_score":0.0165053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03641966218028876,"score_gpt":0.1656292143299598,"score_spread":0.1292095521496711,"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."}}