{"id":"W4206049888","doi":"10.1109/tvt.2021.3134329","title":"GAN and Multi-Agent DRL Based Decentralized Traffic Light Signal Control","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Traffic control and management","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Intersection (aeronautics); Scalability; Reinforcement learning; Intelligent transportation system; Computer network; Bandwidth (computing); Distributed computing; Traffic congestion; Real-time computing; Engineering; Artificial intelligence; Transport engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006764702,0.0006726105,0.0008519666,0.0002708701,0.0003031471,0.0005298834,0.001209113,0.0007161925,0.00154432],"category_scores_gemma":[0.00136787,0.0003442913,0.0004210606,0.0002949577,0.0008065092,0.0006488991,0.000889489,0.001267686,0.0002474666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009056997,"about_ca_system_score_gemma":0.001016075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006423885,"about_ca_topic_score_gemma":0.005913953,"domain_scores_codex":[0.9995875,0.0001108741,0.00001215073,0.000117647,0.00009098629,0.00008085885],"domain_scores_gemma":[0.9993957,0.000252926,0.0001011247,0.00005387413,0.0001441749,0.00005218787],"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":[0.00002539742,0.00001757481,0.0002088065,0.00001543917,0.00001138272,0.00002927008,0.00001657252,0.9826891,0.0009866824,0.005873016,0.0005737156,0.009553036],"study_design_scores_gemma":[0.000002202651,0.000006325281,0.0000169965,5.591143e-7,9.987566e-7,0.000002809024,9.783196e-7,0.9990694,0.00007805857,0.0007449428,0.00007563049,0.000001095401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01966761,0.0001555119,0.9762437,0.0002303605,0.0000440254,0.00002681126,0.00004725255,0.0003854712,0.003199302],"genre_scores_gemma":[0.9569968,0.00007991744,0.03986971,0.000118328,0.00002978728,0.00006697077,0.00008227653,0.00004207833,0.00271411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006423885,"threshold_uncertainty_score":0.01277298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005906070109730275,"score_gpt":0.1911446829526967,"score_spread":0.1852386128429664,"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."}}