{"id":"W1934735491","doi":"10.1002/atr.1276","title":"A reinforcement learning approach for distance‐based dynamic tolling in the stochastic network environment","year":2014,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic control and management","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Toll; Reinforcement learning; Computer science; Benchmark (surveying); Throughput; Markov chain; Markov decision process; Q-learning; Mathematical optimization; Markov process; Simulation; Artificial intelligence; Mathematics; Machine learning; Telecommunications","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":[0.0003279371,0.00008582739,0.0001381757,0.00004638211,0.00003883123,0.0000104409,0.00007945249,0.00001944503,0.000001894223],"category_scores_gemma":[0.000005920737,0.00006675609,0.00007044329,0.00006205351,0.000007214375,0.00009039346,4.428788e-7,0.0001335762,1.95096e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005818409,"about_ca_system_score_gemma":0.000004469929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.533594e-7,"about_ca_topic_score_gemma":0.00001306952,"domain_scores_codex":[0.9992751,0.00001444783,0.0003402522,0.00006382848,0.0001614651,0.0001448351],"domain_scores_gemma":[0.9997204,0.00007283976,0.0001132512,0.00005906061,0.00001286941,0.00002159174],"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":[0.00008698538,0.00001619054,0.00001824598,0.00005930225,0.00001571178,9.290174e-7,0.0004988884,0.9855316,0.0001238333,0.0003241934,0.000004757182,0.01331932],"study_design_scores_gemma":[0.001633487,0.000152368,0.008688753,0.00005563006,0.00005240888,4.745362e-7,0.0003213055,0.9861641,0.000003605991,0.0001599835,0.002681532,0.00008636787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02694453,0.0001977701,0.9723671,0.00004614229,0.0001121958,0.0002753586,6.286501e-7,0.00001561051,0.00004063435],"genre_scores_gemma":[0.9825109,0.00003358662,0.01728357,0.00002611506,0.00005890642,0.00004200343,0.00002590689,0.00001174243,0.000007257048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555664,"threshold_uncertainty_score":0.2722234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004851720496764469,"score_gpt":0.1931793740494931,"score_spread":0.1883276535527287,"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."}}