{"id":"W3159284201","doi":"10.24963/ijcai.2021/60","title":"Reducing Bus Bunching with Asynchronous Multi-Agent Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Asynchronous communication; Artificial neural network; Local bus; Distributed computing; Reliability (semiconductor); Control bus; System bus; Computer network; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000119445,0.000296144,0.0002782004,0.0001432353,0.0001113,0.0001369828,0.0001299283,0.000164404,0.0004696458],"category_scores_gemma":[0.00001738969,0.000291182,0.00008496441,0.0001875083,0.00002202652,0.00009308624,0.00005290315,0.0009268529,0.00001614642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002313697,"about_ca_system_score_gemma":0.000139383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002974362,"about_ca_topic_score_gemma":0.000337686,"domain_scores_codex":[0.9986545,0.00001676398,0.0004739131,0.0003541695,0.0002316556,0.000268936],"domain_scores_gemma":[0.9992834,0.00002029454,0.00007408457,0.0003937778,0.0001494686,0.00007901925],"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":[0.000002185841,0.00002445956,0.0003557038,0.0002875394,0.0001668438,0.00001455238,0.002256382,0.9922799,0.001237918,0.0001615614,0.00004081447,0.003172117],"study_design_scores_gemma":[0.001347439,0.00008812742,0.01629079,0.00128697,0.0002255101,0.00002190742,0.004538996,0.9599583,0.009682402,0.00001248845,0.004951129,0.001595922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2500963,0.0001532266,0.742373,0.00005480395,0.000525211,0.0003571303,0.000003036976,0.000883289,0.005553963],"genre_scores_gemma":[0.96012,0.0001146069,0.03799863,0.00004641842,0.0000625672,0.000113906,0.0005626352,0.00005882048,0.0009224343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7100237,"threshold_uncertainty_score":0.999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01807650911637214,"score_gpt":0.2371433459599049,"score_spread":0.2190668368435328,"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."}}