{"id":"W3128838395","doi":"","title":"Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning.","year":2020,"lang":"en","type":"article","venue":"IV","topic":"Traffic control and management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Jerk; Reinforcement learning; Acceleration; Control theory (sociology); Collision avoidance; Computer science; Control (management); Motion control; Function (biology); Engineering; Artificial intelligence; Simulation; Collision; Robot","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":[0.00004169841,0.0001024957,0.0001180631,0.00003386321,0.00004950329,0.0000286202,0.00008049857,0.00002284602,0.0001147511],"category_scores_gemma":[0.00001367949,0.0001039156,0.00004378129,0.0000946282,0.000006246458,0.00004574929,0.00003155177,0.0001219292,0.0001381426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003311085,"about_ca_system_score_gemma":0.000003528193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006023653,"about_ca_topic_score_gemma":0.000001567195,"domain_scores_codex":[0.9994373,0.000007296325,0.0001220737,0.0001169434,0.0001224106,0.0001940283],"domain_scores_gemma":[0.9998051,0.00001356473,0.00001569619,0.00008843864,0.000007482076,0.00006970453],"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":[0.000004371777,0.00000319326,0.00002913669,0.00003093941,0.00003987779,0.00001169624,0.0004415873,0.9797308,0.001982153,0.0002805521,0.0004284069,0.01701722],"study_design_scores_gemma":[0.0003168347,0.00003251064,0.0002671172,0.00001581136,0.00001762892,4.405612e-7,0.00007952107,0.9100841,0.00025344,0.000003590492,0.08880245,0.0001265253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6213374,0.0009150596,0.2972355,0.001950307,0.00134487,0.0006168413,0.000001009864,0.002790642,0.07380842],"genre_scores_gemma":[0.9990716,0.00002634977,0.0002685906,0.0003265911,0.0001500503,0.000004352396,0.000002653738,0.00002167135,0.000128154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3777342,"threshold_uncertainty_score":0.4237554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01442125314716658,"score_gpt":0.2062512811769602,"score_spread":0.1918300280297937,"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."}}