{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001116161,0.00007469673,0.0001200931,0.0001339898,0.00001406768,0.000007822045,0.00004206828,0.000009139804,0.00003139281],"category_scores_gemma":[0.000002800159,0.00006739219,0.00001370414,0.000174969,0.000006256294,0.00008556525,0.00001952384,0.00005309379,0.0000176724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000515789,"about_ca_system_score_gemma":0.000002431383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003940689,"about_ca_topic_score_gemma":0.0009651237,"domain_scores_codex":[0.9995016,0.000006788663,0.0001536768,0.00006734573,0.00007954822,0.0001910597],"domain_scores_gemma":[0.9997831,0.00001959714,0.00002357641,0.000105462,0.00001356154,0.00005470268],"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":[0.00001170245,0.00001286453,0.002588028,0.00003544312,0.00002835363,4.159535e-7,0.0004952004,0.9781444,0.006337743,0.004441419,0.0001140448,0.007790376],"study_design_scores_gemma":[0.00422789,0.000434254,0.4005742,0.0002303917,0.0001266983,0.000003114972,0.002328931,0.4083992,0.01901645,0.00007301809,0.1634194,0.001166469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4121642,0.00002567093,0.5358617,0.00009897383,0.00006430926,0.0006965672,0.000001414861,0.0003393443,0.05074785],"genre_scores_gemma":[0.9968304,0.00001235083,0.001376462,0.00001619296,0.00001307521,0.0001121685,0.00000733764,0.0000124742,0.001619555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5846662,"threshold_uncertainty_score":0.2748173,"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."}}