{"id":"W4200507047","doi":"10.32920/17313137.v1","title":"Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Obstacle; Train; Obstacle avoidance; Perception; Trajectory; Action (physics); Object (grammar); Robot; Mobile 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007411675,0.0006648758,0.0005947437,0.0002581644,0.0002605486,0.0005794946,0.001051987,0.0006726925,0.00103593],"category_scores_gemma":[0.001868069,0.0004328778,0.0003964096,0.0001428271,0.0007235366,0.0007331168,0.001008034,0.001076788,0.0002176843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007834156,"about_ca_system_score_gemma":0.001070376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005861239,"about_ca_topic_score_gemma":0.004983307,"domain_scores_codex":[0.9997404,0.0000605381,0.0000108786,0.00006846833,0.00007113146,0.00004852535],"domain_scores_gemma":[0.9994548,0.000233132,0.00008662238,0.00004675655,0.0001218166,0.00005688619],"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":[0.00002818694,0.00003142877,0.0006258788,0.00001765769,0.00001482172,0.00004284515,0.00003534808,0.9778607,0.001624242,0.003383567,0.0002926765,0.0160425],"study_design_scores_gemma":[0.000001836508,0.000009157711,0.00002321038,0.000001052739,9.879167e-7,0.000002549581,0.000001226729,0.9992114,0.0001282872,0.0005549343,0.00006438669,9.924796e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05058708,0.0001978477,0.9456073,0.0002274314,0.00004287862,0.00003504333,0.00002363003,0.0006439959,0.002634667],"genre_scores_gemma":[0.9453338,0.00007236638,0.05210346,0.00009071759,0.00001535055,0.00005088053,0.00004479712,0.00004977617,0.00223887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005861239,"threshold_uncertainty_score":0.01165426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0186631170123467,"score_gpt":0.2561486766434662,"score_spread":0.2374855596311195,"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."}}