{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000148794,0.0004038476,0.0004259207,0.0003330199,0.0001215362,0.00006888349,0.0004396187,0.0002108227,0.0001165269],"category_scores_gemma":[0.00001150406,0.0004971073,0.0002289944,0.0002269679,0.00002978346,0.000116397,0.0005124987,0.0007686047,0.0002071922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000415043,"about_ca_system_score_gemma":0.00003372906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006084972,"about_ca_topic_score_gemma":0.00001275354,"domain_scores_codex":[0.9985586,0.00004272342,0.0002199447,0.0006011825,0.0001112744,0.0004663051],"domain_scores_gemma":[0.9990733,0.00005153521,0.0001121469,0.0006064135,0.00004340267,0.000113152],"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":[0.00001775374,0.00001634461,0.0002987323,0.0002141773,0.0002853386,0.0001023896,0.0001538782,0.9942929,0.0001035952,0.003467494,0.00007614444,0.000971266],"study_design_scores_gemma":[0.0006030095,0.00003036774,0.00039808,0.0001918494,0.0001760873,8.644763e-7,0.0001591981,0.9938889,0.00004068499,0.0001430081,0.003844979,0.0005229382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6291049,0.0001451009,0.3460168,0.00001427654,0.001569111,0.0005149858,0.000002141871,0.0008352258,0.02179744],"genre_scores_gemma":[0.9972751,0.0003043783,0.0001057351,0.0000354554,0.0001140354,9.328203e-7,0.00002515966,0.00006181851,0.002077347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3681703,"threshold_uncertainty_score":0.9997481,"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."}}