{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005425733,0.0006128871,0.0006962974,0.001483584,0.0009935178,0.0003918233,0.0004867778,0.0002542372,0.0001787484],"category_scores_gemma":[0.0001576175,0.0006088979,0.0002037566,0.001892043,0.0004247986,0.001138507,0.00002053263,0.001980313,0.00007768012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003745015,"about_ca_system_score_gemma":0.0001677875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002842535,"about_ca_topic_score_gemma":0.003897667,"domain_scores_codex":[0.9910954,0.0008045314,0.001250058,0.001049842,0.003794861,0.002005333],"domain_scores_gemma":[0.9959816,0.0006229672,0.0002097069,0.0005297611,0.00207698,0.0005789422],"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":[0.00126067,0.0001114606,0.002955798,0.0008306489,0.0002964837,0.00005575065,0.006915249,0.9502932,0.01759178,0.00156008,0.0004932841,0.01763556],"study_design_scores_gemma":[0.009951114,0.004650734,0.1458867,0.001288849,0.0003454495,0.000002401689,0.02198882,0.7534395,0.01064664,0.0005192454,0.04883559,0.002444999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7851084,0.0001154309,0.2100806,0.0002340737,0.0002157195,0.001914983,0.00003810431,0.0008950951,0.001397533],"genre_scores_gemma":[0.9921135,0.0002039931,0.005123346,0.00002659845,0.0002229523,0.0003813301,0.0004042608,0.0002011234,0.001322839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2070051,"threshold_uncertainty_score":0.9996362,"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."}}