{"id":"W3209319237","doi":"10.1155/2021/6669028","title":"A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic control and management","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Science and Technology Commission of Shanghai Municipality; Natural Science Foundation of Shanghai","keywords":"Metering mode; Computer science; Real-time computing; Reinforcement learning; Traffic flow (computer networking); Queue; Floating car data; Artificial intelligence; Simulation; Traffic congestion; Transport engineering; Computer network; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001972093,0.0001131209,0.0001982614,0.00009396129,0.00004123442,0.00002274306,0.0001300283,0.00002962409,0.00001111766],"category_scores_gemma":[0.00002664163,0.0001109105,0.00009647568,0.0001106273,0.000005111197,0.0002796508,0.000001949507,0.0001498538,4.002309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004552868,"about_ca_system_score_gemma":0.00002181756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.059019e-7,"about_ca_topic_score_gemma":0.00001021073,"domain_scores_codex":[0.9990875,0.00001148436,0.0004095959,0.0001332314,0.0002096892,0.0001485616],"domain_scores_gemma":[0.9995213,0.00005679544,0.0001175677,0.0001683553,0.00008289707,0.0000530504],"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":[0.000138033,0.00003352816,0.000003266007,0.0001634796,0.00006927114,0.00001545883,0.0002381422,0.9294565,0.002519065,0.0000371283,0.00002713376,0.06729895],"study_design_scores_gemma":[0.002456675,0.0001756983,0.001351155,0.00007243092,0.0001217638,0.000002413528,0.0003751947,0.9879192,0.0004334091,0.000007207774,0.006956381,0.0001284754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02918279,0.0002803872,0.9697992,0.00005930142,0.000290935,0.0001840062,0.000003567261,0.00006172088,0.0001381055],"genre_scores_gemma":[0.9384761,0.00009625257,0.06098317,0.00003844014,0.00007946499,0.00001411094,0.0002672827,0.00002248048,0.00002271837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9092933,"threshold_uncertainty_score":0.4522799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01539743578726217,"score_gpt":0.2319186524903297,"score_spread":0.2165212167030676,"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."}}