{"id":"W7117129885","doi":"10.1061/jtepbs.teeng-9335","title":"Deep Reinforcement Learning for Trajectory Control of Connected and Automated Vehicles at a Mixed-Traffic Intersection","year":2025,"lang":"en","type":"article","venue":"Journal of Transportation Engineering Part A Systems","topic":"Traffic control and management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Intersection (aeronautics); Reinforcement learning; Trajectory; Acceleration; Focus (optics); Control (management); Intelligent transportation system; Optimal control; Function (biology)","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":[0.0002375099,0.0001289972,0.0003331624,0.0002688613,0.00003018266,0.00001568376,0.00005142015,0.00005855172,0.000001688339],"category_scores_gemma":[0.00001881768,0.0001276045,0.0001049183,0.0001216019,0.000009229604,0.00008893742,0.000001171821,0.00009776391,1.922746e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009195169,"about_ca_system_score_gemma":0.00001227665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003750915,"about_ca_topic_score_gemma":0.00002375995,"domain_scores_codex":[0.9989729,0.00001434552,0.000679762,0.00007640959,0.0001222242,0.000134362],"domain_scores_gemma":[0.9995194,0.0001067971,0.0001626481,0.00005248721,0.0001130488,0.00004563321],"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":[0.0000804686,0.00001103741,0.000153425,0.001005223,0.0004244501,0.00000217967,0.000425633,0.9881492,0.008680132,0.0001604103,0.0002626079,0.0006452954],"study_design_scores_gemma":[0.002200218,0.0001162069,0.007961425,0.0004165389,0.0001964417,0.000004858017,0.0002558314,0.9833937,0.0003596021,3.369308e-7,0.004994195,0.0001006863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5480715,0.001437745,0.4486514,0.00001280211,0.001231763,0.000331711,0.000003440446,0.0002419478,0.00001769843],"genre_scores_gemma":[0.9996751,0.0000509971,0.0001177466,0.000002832476,0.00004866449,0.00003563752,0.00001236951,0.00001685669,0.00003978582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4516036,"threshold_uncertainty_score":0.5203561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00456102774556207,"score_gpt":0.1885686636003426,"score_spread":0.1840076358547805,"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."}}