{"id":"W620951045","doi":"","title":"Closed-Loop Optimal Freeway Ramp Metering Using Continuous State Space Reinforcement Learning with Function Approximation","year":2014,"lang":"en","type":"article","venue":"Transportation Research Board 93rd Annual MeetingTransportation Research Board","topic":"Traffic control and management","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Function approximation; Computer science; Artificial neural network; Representation (politics); State space; Benchmark (surveying); Mathematical optimization; Tree (set theory); Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008771419,0.0005628475,0.0007566618,0.0002700182,0.0002504424,0.0007687535,0.0007621853,0.0007020312,0.001308783],"category_scores_gemma":[0.001830103,0.0003001976,0.0004227285,0.0002888729,0.0006223744,0.0006959846,0.0004588683,0.0008437588,0.0001864982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008602405,"about_ca_system_score_gemma":0.001239816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01902159,"about_ca_topic_score_gemma":0.008709429,"domain_scores_codex":[0.9996194,0.0001133675,0.0000180783,0.0000879263,0.0001051377,0.00005605468],"domain_scores_gemma":[0.9993531,0.0003943665,0.00007601139,0.00003620701,0.0001143283,0.00002592771],"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":[0.00003328273,0.00001939708,0.000173357,0.00001816638,0.000009356353,0.00001210803,0.0000155755,0.9855612,0.0004108189,0.0007372358,0.000151303,0.01285821],"study_design_scores_gemma":[0.000004542786,0.00001778796,0.00003489034,0.000001235999,0.000001574491,0.000001812306,0.000001547999,0.9995895,0.0001265593,0.0001621963,0.00005718357,0.000001170457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05910322,0.0002689375,0.9355834,0.0001347205,0.00004081853,0.00005858773,0.00003164088,0.0009918527,0.003786808],"genre_scores_gemma":[0.9641446,0.00006049272,0.03463129,0.00004050875,0.000008243245,0.00004939664,0.00003662346,0.00002636337,0.001002403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01902159,"threshold_uncertainty_score":0.03782171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02551131076780351,"score_gpt":0.2860105765632764,"score_spread":0.2604992657954729,"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."}}