{"id":"W3086911381","doi":"10.1109/access.2020.3022755","title":"Decision-Making Strategy on Highway for Autonomous Vehicles Using Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Traffic control and management","field":"Engineering","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"State Key Laboratory of Mechanical System and Vibration","keywords":"Overtaking; Reinforcement learning; Computer science; Acceleration; Control (management); Convergence (economics); Vehicle dynamics; Artificial intelligence; Transport engineering; Simulation; Automotive engineering; Engineering","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":[0.0006790332,0.0005155821,0.0005344465,0.0002508503,0.0004004435,0.000508179,0.0007879565,0.0006934928,0.001529303],"category_scores_gemma":[0.001401175,0.0002467732,0.0003086392,0.0001750188,0.0005740605,0.0006655158,0.0007565868,0.0008911832,0.0001549509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009013162,"about_ca_system_score_gemma":0.001602934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110844,"about_ca_topic_score_gemma":0.008502595,"domain_scores_codex":[0.9997162,0.00006437623,0.00001492971,0.00007206221,0.00005570586,0.00007680345],"domain_scores_gemma":[0.999459,0.0002139399,0.00008538965,0.00002635543,0.000155629,0.00005970569],"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":[0.00005731773,0.00004998331,0.001372053,0.00003716169,0.00001795653,0.00006633576,0.00005646366,0.9655122,0.002050425,0.005082917,0.0005737611,0.02512352],"study_design_scores_gemma":[0.000004897535,0.0000188451,0.00008170129,0.000001819212,0.000002661046,0.000003970001,0.00000497199,0.9986225,0.0001997888,0.0009604266,0.00009641392,0.00000198804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07536373,0.000239617,0.9195247,0.0003871897,0.00005899944,0.00005732547,0.00004638225,0.0003117997,0.004010217],"genre_scores_gemma":[0.9768497,0.00006966443,0.0216339,0.00008969394,0.00001312997,0.0000465484,0.00004337241,0.00001268536,0.001241184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0110844,"threshold_uncertainty_score":0.02203977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0341180750519232,"score_gpt":0.2838612322417892,"score_spread":0.249743157189866,"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."}}