{"id":"W2037898135","doi":"10.1109/itsc.2012.6338837","title":"Application of reinforcement learning with continuous state space to ramp metering in real-world conditions","year":2012,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Testbed; Representation (politics); Computer science; State space; Convergence (economics); Metering mode; State (computer science); Focus (optics); Controller (irrigation); Artificial intelligence; Algorithm; Mathematics; Engineering; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157275,0.0004979686,0.0005028314,0.0002752156,0.0001960979,0.0004478965,0.0008575832,0.0006002528,0.0006350741],"category_scores_gemma":[0.004051447,0.0002001741,0.0002144458,0.0002317129,0.0007494853,0.0006579728,0.000568771,0.0008164773,0.00008482892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005704472,"about_ca_system_score_gemma":0.0005970388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005720594,"about_ca_topic_score_gemma":0.004028594,"domain_scores_codex":[0.9994286,0.0002918512,0.00002519186,0.00009810889,0.0001165769,0.00003975747],"domain_scores_gemma":[0.9979236,0.001410694,0.0002076102,0.0001710017,0.0002076339,0.00007948388],"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":[0.00008385193,0.00008771832,0.001068167,0.00004902033,0.000032075,0.00005981351,0.00003991193,0.9587854,0.001812613,0.001456702,0.0001675307,0.03635717],"study_design_scores_gemma":[0.000007046025,0.00003139388,0.0001376066,0.000001533811,0.000002381003,0.000006082163,0.000004076962,0.9988388,0.0004922811,0.0003805703,0.00009543628,0.000002708197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06604291,0.0002144009,0.9315261,0.0001635398,0.0000482595,0.00005348676,0.00001301302,0.000592091,0.001346149],"genre_scores_gemma":[0.9438178,0.00005766218,0.0556836,0.00003323612,0.00001533668,0.0000292626,0.00001253605,0.0000162625,0.0003342228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005720594,"threshold_uncertainty_score":0.01137459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006605577791145977,"score_gpt":0.2205989341011834,"score_spread":0.2139933563100375,"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."}}