{"id":"W4313125087","doi":"10.1109/tits.2022.3229527","title":"Robust Dynamic Bus Control: a Distributional Multi-Agent Reinforcement Learning Approach","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Traffic control and management","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; Canada Foundation for Innovation","keywords":"Reinforcement learning; Computer science; Control (management); Vehicle dynamics; Artificial intelligence; Engineering; Automotive 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002937399,0.0003074061,0.0003121632,0.0002566475,0.0004703159,0.00005548255,0.000200957,0.00006335584,0.000282949],"category_scores_gemma":[9.025116e-7,0.0003399805,0.0002442091,0.0003336163,0.00002840415,0.0001101352,5.006832e-7,0.000516694,0.00004892785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005641373,"about_ca_system_score_gemma":0.00002814664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009071332,"about_ca_topic_score_gemma":0.00005422734,"domain_scores_codex":[0.9978147,0.00009054511,0.0007270867,0.0003655184,0.0006218108,0.0003803387],"domain_scores_gemma":[0.9994448,0.00004392782,0.00009175634,0.0002244485,0.00006561288,0.0001294887],"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":[0.00008454965,0.0002321402,0.00001195919,0.0001274503,0.0003137784,0.00000978948,0.000613875,0.9946368,0.0002425742,0.0003022233,0.0001117231,0.003313087],"study_design_scores_gemma":[0.001412353,0.0001255447,0.000379509,0.00002475359,0.0001454227,0.000008396641,0.001649764,0.9795554,0.0001107511,0.000001370719,0.01622933,0.0003574203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005218621,0.0002790098,0.9896421,0.00003088975,0.002425476,0.001125727,0.000332261,0.0007405673,0.000205323],"genre_scores_gemma":[0.9957442,0.0001012232,0.0001969764,0.00002708234,0.00002849184,0.001751897,0.0004156647,0.00005482492,0.001679626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9905256,"threshold_uncertainty_score":0.9999052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02057679221190197,"score_gpt":0.210405954126524,"score_spread":0.1898291619146221,"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."}}