{"id":"W4206744121","doi":"10.1109/tsusc.2021.3138926","title":"FECO: An Efficient Deep Reinforcement Learning-Based Fuel-Economic Traffic Signal Control Scheme","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Computing","topic":"Traffic control and management","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Canada Research Chairs","keywords":"Reinforcement learning; Fuel efficiency; SIGNAL (programming language); Computer science; Efficient energy use; Control (management); Economic shortage; Traffic signal; Traffic optimization; Real-time computing; Floating car data; Automotive engineering; Transport engineering; Engineering; Traffic congestion; Artificial intelligence; Electrical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0005942496,0.000786954,0.0008602873,0.0003790811,0.0003225955,0.0004677639,0.001747872,0.0008973941,0.00208374],"category_scores_gemma":[0.001331252,0.0002745769,0.0003618913,0.0002551163,0.0004957017,0.000738715,0.0009462869,0.001362705,0.0003729789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000781394,"about_ca_system_score_gemma":0.001244036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007738646,"about_ca_topic_score_gemma":0.00956335,"domain_scores_codex":[0.9997303,0.00003764803,0.00001149902,0.00006949605,0.00007633797,0.00007466568],"domain_scores_gemma":[0.9996492,0.0001162945,0.00004168361,0.00003680626,0.0001034418,0.00005255666],"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":[0.0001620421,0.000181957,0.001101229,0.00006258705,0.00004422762,0.000117102,0.00004411708,0.84574,0.004454015,0.008131478,0.005036952,0.1349242],"study_design_scores_gemma":[0.000009047993,0.00002009381,0.00005191137,0.000002413841,0.000003031698,0.000008670116,0.000001799802,0.9984494,0.00031983,0.0007654296,0.000365459,0.000002867076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0438711,0.0005608418,0.9441471,0.0004209116,0.0001950963,0.000114849,0.0001568577,0.002140875,0.008392256],"genre_scores_gemma":[0.9194076,0.0001528333,0.07425804,0.0003509811,0.0000548118,0.0001304052,0.0002335685,0.00009343154,0.005318293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007738646,"threshold_uncertainty_score":0.01538724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005138195873247886,"score_gpt":0.1980370189845221,"score_spread":0.1928988231112742,"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."}}