{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001203483,0.0008180096,0.001065726,0.0003847134,0.0003165093,0.0007200856,0.00151955,0.001018862,0.001593367],"category_scores_gemma":[0.002781785,0.0004459373,0.0005238191,0.0003090821,0.0009172662,0.00084508,0.00111759,0.001479671,0.0001868763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001009337,"about_ca_system_score_gemma":0.0009406503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007882835,"about_ca_topic_score_gemma":0.004550146,"domain_scores_codex":[0.999543,0.0001405436,0.0000189251,0.0001184392,0.00009272655,0.00008647616],"domain_scores_gemma":[0.9987412,0.0006485629,0.0002002236,0.00007497765,0.0002567645,0.00007821062],"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":[0.00001638193,0.0000134663,0.0002419778,0.00001322322,0.00001470479,0.00002365433,0.00001449743,0.9908371,0.0001982276,0.003203566,0.0001718122,0.005251537],"study_design_scores_gemma":[0.000002322821,0.000007052855,0.00002218303,9.694085e-7,0.000001500124,0.00000175352,0.000001272292,0.9991304,0.00003012226,0.000751107,0.0000501767,0.000001130219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0309394,0.0003649311,0.9644607,0.000456515,0.00004737523,0.0000325622,0.00004656031,0.0003832451,0.003268714],"genre_scores_gemma":[0.974294,0.0001138294,0.02362387,0.0001303769,0.00003849383,0.00005379607,0.00005133668,0.0000379077,0.001656487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007882835,"threshold_uncertainty_score":0.01567388,"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."}}