{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007492049,0.0001622229,0.0001779546,0.00006600327,0.0001123088,0.0001873331,0.0002777026,0.00004736456,0.0000379652],"category_scores_gemma":[0.00002889902,0.0001599119,0.0000718938,0.0001220139,0.000008591182,0.0002206774,0.00004385811,0.0001309113,0.00001901953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008104325,"about_ca_system_score_gemma":0.00001329245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007189833,"about_ca_topic_score_gemma":0.00001149297,"domain_scores_codex":[0.9990997,0.000008624485,0.0002452347,0.0002130304,0.0001528527,0.0002805638],"domain_scores_gemma":[0.9995946,0.0001345998,0.00004523753,0.0001249495,0.00002578451,0.00007484736],"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":[0.00004139833,0.000005443311,0.00001281109,0.00005712678,0.00004088322,0.000007132353,0.0001102015,0.8294981,0.000696516,0.0002998594,0.0004009955,0.1688295],"study_design_scores_gemma":[0.0005479939,0.00009237412,0.0002619932,0.00006200666,0.00002985357,5.251371e-7,0.00004650716,0.9892122,0.0006671821,0.0001522272,0.008725822,0.0002013856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1897102,0.0001353418,0.8062364,0.00007883486,0.0006993015,0.0004339782,0.000001542646,0.0006213087,0.002083057],"genre_scores_gemma":[0.9985477,0.00001340687,0.0008005134,0.0002653403,0.000276561,0.00003571664,0.000002840643,0.00003851112,0.00001941824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8088375,"threshold_uncertainty_score":0.652102,"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."}}