{"id":"W4398147587","doi":"10.1016/j.physa.2024.129734","title":"Cooperative traffic optimization with multi-agent reinforcement learning and evolutionary strategy: Bridging the gap between micro and macro traffic control","year":2024,"lang":"en","type":"article","venue":"Physica A Statistical Mechanics and its Applications","topic":"Traffic control and management","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; Ministry of Science and Technology of the People's Republic of China","keywords":"Bridging (networking); Macro; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Computer network; Structural 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008264098,0.0001736656,0.0001680103,0.00003924501,0.0002615413,0.0001573825,0.0000478979,0.00002976757,0.000009796777],"category_scores_gemma":[0.000006827882,0.0001296087,0.00001518453,0.0001336326,0.00003519741,0.00008200522,0.0000264769,0.0001836107,0.000003791607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000300992,"about_ca_system_score_gemma":0.00001765025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002074446,"about_ca_topic_score_gemma":0.000004114921,"domain_scores_codex":[0.999217,0.00002561521,0.000181195,0.0002720963,0.0001092892,0.0001948427],"domain_scores_gemma":[0.9995587,0.0002094792,0.00002253949,0.00007470293,0.00004021409,0.00009435102],"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":[0.000007488477,0.00001984517,4.278299e-7,0.0001142524,0.0001363993,0.00000152371,0.0001997012,0.8645435,0.0003549604,0.0875387,0.0001009299,0.04698228],"study_design_scores_gemma":[0.0004871001,0.00009822386,0.0001013614,0.0000351244,0.0001859735,0.000003975406,0.0001566178,0.9963323,0.000009767381,0.0001499122,0.002273627,0.0001659591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004315123,0.001611132,0.992328,0.0004232824,0.00001830919,0.0009248322,0.0001439894,0.0001945333,0.00004075219],"genre_scores_gemma":[0.9962512,0.0006522576,0.002470135,0.00002383571,0.00006911918,0.0003818978,0.00008002202,0.00002697216,0.00004457522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9919361,"threshold_uncertainty_score":0.528529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01127128508230215,"score_gpt":0.2337799629367886,"score_spread":0.2225086778544865,"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."}}