{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001212268,0.000812973,0.00100255,0.0003877596,0.0003538135,0.0007222632,0.001132971,0.0009769059,0.001651984],"category_scores_gemma":[0.002682365,0.0003868485,0.0004783551,0.0002775953,0.001178532,0.0008771665,0.0009818336,0.001065222,0.0002140563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001213128,"about_ca_system_score_gemma":0.001186282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005044799,"about_ca_topic_score_gemma":0.003807785,"domain_scores_codex":[0.9994092,0.0003039553,0.00001813506,0.0000941326,0.00009429307,0.00008040669],"domain_scores_gemma":[0.9988545,0.0007090031,0.0001586405,0.00004982519,0.0001385972,0.00008946511],"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":[0.00001770124,0.0000175338,0.0002627457,0.0000152783,0.00001470258,0.0000287704,0.00002235778,0.9862423,0.0002064123,0.008529547,0.0001538919,0.00448878],"study_design_scores_gemma":[0.000003288904,0.000009452961,0.00002162643,0.000001587039,0.000001403258,0.000002428467,0.000002543556,0.9967123,0.00002925735,0.003125059,0.00008960401,0.000001473686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02078355,0.0001370992,0.9763408,0.000227288,0.00002663806,0.00003165099,0.00002337825,0.0001414392,0.002288155],"genre_scores_gemma":[0.9548534,0.000110705,0.04282584,0.00008057519,0.00003375073,0.0001332041,0.00004071527,0.00002656933,0.001895146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005044799,"threshold_uncertainty_score":0.01003087,"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."}}