{"id":"W4391305615","doi":"10.1109/tase.2023.3347264","title":"Socially Intelligent Reinforcement Learning for Optimal Automated Vehicle Control in Traffic Scenarios","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Traffic control and management","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Control (management); Computer science; Intelligent transportation system; Engineering; Reinforcement; Control engineering; Artificial intelligence; Transport engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004374696,0.000137228,0.000128234,0.0004996251,0.000181602,0.0001551961,0.00008943142,0.00004453244,0.000009567468],"category_scores_gemma":[0.000009568955,0.0001419221,0.00004515536,0.0005495211,0.00003313765,0.0003687491,0.000001299645,0.000159058,0.00001020596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002374032,"about_ca_system_score_gemma":0.0000585962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003604399,"about_ca_topic_score_gemma":0.000008650847,"domain_scores_codex":[0.999016,0.000005216748,0.0002429423,0.0002063399,0.0002337961,0.0002957459],"domain_scores_gemma":[0.9997373,0.00007451549,0.00001072635,0.00007108763,0.00003676784,0.00006966407],"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":[0.000005240512,0.000009083053,1.880267e-7,0.000101442,0.00001927873,0.000001739368,0.0008400048,0.9273284,0.008240802,0.0001222393,0.00002471721,0.06330688],"study_design_scores_gemma":[0.0003967319,0.00005654197,0.0001318293,0.00009505985,0.00001723877,0.000001967515,0.0001001724,0.9966536,0.0009967709,0.000001487305,0.001397162,0.0001513989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1358699,0.00009089478,0.8605058,0.0001506839,0.0006289817,0.0003853071,0.000002003794,0.002322458,0.00004397648],"genre_scores_gemma":[0.9990087,0.00004921942,0.0006801515,0.00002458112,0.00002296109,0.0001509974,0.000001037873,0.00002016554,0.00004218399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8631388,"threshold_uncertainty_score":0.5787415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008588271819652122,"score_gpt":0.2280807105345134,"score_spread":0.2194924387148613,"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."}}