{"id":"W2049593940","doi":"10.1109/itsc.2012.6338707","title":"Multi-Agent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC)","year":2012,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Network traffic control; Computer science; Adaptive control; Controller (irrigation); Real-time computing; Traffic congestion; SIGNAL (programming language); Traffic optimization; Engineering; Simulation; Computer network; Control (management); Floating car data; Transport engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003323637,0.0002042434,0.0003159326,0.00005395831,0.00005833865,0.00001298591,0.0001056637,0.00006257043,0.0002173645],"category_scores_gemma":[0.0000155258,0.000172919,0.0001582688,0.0001169624,0.00002264549,0.0001011223,0.000023508,0.0001325826,0.0000182353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000957409,"about_ca_system_score_gemma":0.00001357928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001419326,"about_ca_topic_score_gemma":0.0000337288,"domain_scores_codex":[0.9988175,0.00002513054,0.0003774369,0.0001256386,0.0001379261,0.0005163508],"domain_scores_gemma":[0.9995494,0.0001133809,0.00006293501,0.0001122034,0.00006466535,0.00009739638],"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":[0.0001251819,0.00004336761,0.00003026277,0.00003450355,0.0003111195,3.639448e-7,0.0003076835,0.958049,0.0004282143,0.0009297375,0.002795026,0.03694556],"study_design_scores_gemma":[0.002832754,0.0001705757,0.0004385794,0.00002862703,0.0000894742,3.301566e-7,0.0006153132,0.9621447,0.0001200754,0.000002418619,0.03335558,0.0002015248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02082562,0.0009629743,0.9726324,0.0000379844,0.0006809062,0.001255799,0.000003350611,0.0005234794,0.003077487],"genre_scores_gemma":[0.9909626,0.00003791641,0.006857817,0.00004094112,0.0001692761,0.0001459594,0.00002178449,0.00003183539,0.001731873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.970137,"threshold_uncertainty_score":0.7051433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01720445734778344,"score_gpt":0.2107130546546959,"score_spread":0.1935085973069124,"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."}}