{"id":"W3007054387","doi":"10.1155/2020/8674512","title":"Multiagent Reinforcement Learning-Based Taxi Predispatching Model to Balance Taxi Supply and Demand","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Changchun Science and Technology Bureau; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Taxis; Reinforcement learning; Computer science; Scheduling (production processes); Operations research; Profit (economics); Public transport; Transport engineering; Engineering; Artificial intelligence; Operations management; Economics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009571733,0.0001284614,0.0001838505,0.00009028389,0.00005267315,0.00001610101,0.00006475117,0.00003986562,0.00001683814],"category_scores_gemma":[0.0000244541,0.0001324838,0.00005695076,0.0001954534,0.00001255927,0.0003173862,6.966403e-7,0.0002218696,0.00000140177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003220026,"about_ca_system_score_gemma":0.00003426744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001960892,"about_ca_topic_score_gemma":0.00002955604,"domain_scores_codex":[0.9989624,0.00000770975,0.0005552634,0.0001119033,0.0002291169,0.0001336098],"domain_scores_gemma":[0.9994637,0.00002369988,0.0001335705,0.00005511785,0.0001516516,0.0001722762],"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":[0.00009782643,0.00001361089,0.003527458,0.0001018462,0.00002346772,0.000006193529,0.003831378,0.9679514,0.02280406,0.00009139425,0.0000497093,0.001501652],"study_design_scores_gemma":[0.002596624,0.0003704454,0.1445546,0.0001607528,0.00008595583,0.000001870014,0.0006433021,0.8372478,0.01102756,0.00006724123,0.002947494,0.0002963061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4738512,0.0000588229,0.5253664,0.0004532037,0.00006209013,0.0001397709,0.00001304141,0.00004374173,0.00001175765],"genre_scores_gemma":[0.9735991,0.00008909377,0.02581826,0.0003529742,0.00003779853,0.00001255058,0.00006113849,0.00002021545,0.000008820096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.499748,"threshold_uncertainty_score":0.5402532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01093284381516087,"score_gpt":0.2308156951688306,"score_spread":0.2198828513536698,"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."}}