{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005643123,0.0005574038,0.0005240334,0.0002166415,0.0002273048,0.0003569433,0.0007119431,0.0004067987,0.000907781],"category_scores_gemma":[0.001055082,0.0002722561,0.0003259099,0.0001491633,0.000432494,0.0003880879,0.0005718946,0.000765973,0.0001198996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005808162,"about_ca_system_score_gemma":0.001004657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008424875,"about_ca_topic_score_gemma":0.007547126,"domain_scores_codex":[0.999811,0.00003697632,0.000007357039,0.00004394289,0.00004931635,0.00005138022],"domain_scores_gemma":[0.999622,0.0001382163,0.00007844071,0.00003749418,0.00008263614,0.00004130288],"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":[0.00004021521,0.00004072028,0.0006915584,0.00001439321,0.00001600027,0.0000291316,0.00001737153,0.9785005,0.002120476,0.0009249891,0.0002193563,0.01738511],"study_design_scores_gemma":[0.000003043766,0.00002046636,0.00008709788,9.175721e-7,0.000001769,0.000002303375,0.000001145066,0.9992835,0.0003307757,0.0002145271,0.00005305261,0.000001475052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2385066,0.0002746552,0.7525888,0.0002333984,0.000074669,0.00006338139,0.00004693518,0.001483931,0.006727584],"genre_scores_gemma":[0.9858585,0.0000175272,0.01333477,0.00002984705,0.000004740087,0.0000162318,0.00001834662,0.00001153356,0.0007084911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008424875,"threshold_uncertainty_score":0.01675171,"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."}}