{"id":"W4309534481","doi":"10.1371/journal.pone.0277813","title":"Effects analysis of reward functions on reinforcement learning for traffic signal control","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Traffic control and management","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Korean National Police Agency","keywords":"Reinforcement learning; Computer science; Intersection (aeronautics); Scalability; Traffic flow (computer networking); Signal timing; Simulation; Traffic signal; Real-time computing; Artificial intelligence; Transport engineering; Computer network; 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":[0.000158319,0.00009254437,0.0002895199,0.0002770025,0.0001077812,0.000007979193,0.00007606132,0.00001572671,0.000209492],"category_scores_gemma":[0.00001836868,0.0001003314,0.0001586847,0.0003250033,0.000006573425,0.0000205684,0.00001646561,0.0001216888,0.000005420731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008005049,"about_ca_system_score_gemma":0.000005438018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002908372,"about_ca_topic_score_gemma":0.000005819842,"domain_scores_codex":[0.9992323,0.00002815279,0.0001897056,0.0001230081,0.0002581654,0.0001686933],"domain_scores_gemma":[0.9995987,0.0001960222,0.00003972144,0.0001074277,0.00002242245,0.00003566862],"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":[0.0001169668,0.0002783567,0.00002810969,0.0001383378,0.00518445,0.000001043061,0.0001179112,0.98414,0.005330032,0.0001269756,0.0002673993,0.004270458],"study_design_scores_gemma":[0.001583562,0.0006220861,0.001116298,0.00001478411,0.004004816,3.533297e-8,0.0000738942,0.9901665,0.0004072083,0.000002119544,0.001894274,0.0001144094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9216981,0.0002805202,0.07371128,0.0001812496,0.0001383185,0.001566981,0.00003413289,0.0005813611,0.001808051],"genre_scores_gemma":[0.9982955,0.000006868464,0.00007291984,0.0000476321,0.00003407973,0.0006351362,0.00004727516,0.00001641042,0.0008441269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07659744,"threshold_uncertainty_score":0.4091394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01170924927935002,"score_gpt":0.1779327342918116,"score_spread":0.1662234850124616,"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."}}