{"id":"W2122463624","doi":"10.1139/l03-014","title":"Reinforcement learning: Introduction to theory and potential for transport applications","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Computer science; Intelligent transportation system; Field (mathematics); Key (lock); Domain (mathematical analysis); Control (management); Artificial intelligence; Transport engineering; Engineering; Computer security","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":[0.0006197093,0.00003838066,0.00005813494,0.0001515456,0.0001785567,0.00002108601,0.00003699561,0.00002885918,0.00006407574],"category_scores_gemma":[0.0001478558,0.00004360697,0.000024256,0.0001159908,0.00001533889,0.00009059265,1.773864e-7,0.00006387913,4.313676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004835956,"about_ca_system_score_gemma":0.0002450622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001602296,"about_ca_topic_score_gemma":0.01318472,"domain_scores_codex":[0.9996079,0.0000166515,0.0001332789,0.00005063105,0.00006950351,0.0001220218],"domain_scores_gemma":[0.9995467,0.000024738,0.00004089583,0.00002563764,0.000104825,0.0002572044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000481282,0.000001053605,0.0003282171,0.000006941422,0.000008937012,0.000001108409,0.002674115,0.9346036,0.00005386929,0.06184097,0.0002015489,0.0002748113],"study_design_scores_gemma":[0.0003355756,0.0000774608,0.002573155,0.00002819941,0.0000529396,0.00001185299,0.001745271,0.001029948,0.00008799573,0.0006578324,0.993243,0.0001567571],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004599885,0.0001011362,0.993564,0.0005216975,0.0002325376,0.0001363937,0.000001500105,0.000009415478,0.0008334011],"genre_scores_gemma":[0.9976068,0.00001589118,0.001646369,0.00002355649,0.0002726642,0.000008075763,0.000004571957,0.000006281923,0.000415766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9930415,"threshold_uncertainty_score":0.7357383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005085514470838052,"score_gpt":0.209596304561675,"score_spread":0.204510790090837,"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."}}