{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001381381,0.0009755553,0.00104267,0.001069454,0.0004937061,0.002262766,0.001590245,0.002381478,0.008191749],"category_scores_gemma":[0.003568299,0.0005579585,0.001309665,0.001558015,0.002915735,0.00282613,0.001324963,0.004263268,0.001706875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887942,"about_ca_system_score_gemma":0.001164738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002888301,"about_ca_topic_score_gemma":0.001205378,"domain_scores_codex":[0.9993747,0.0002398408,0.00005585533,0.0001000418,0.0001850489,0.00004459631],"domain_scores_gemma":[0.9981067,0.001437058,0.00008707466,0.0001187967,0.0001837282,0.0000666585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002204831,0.00004256733,0.0003502994,0.0003604275,0.00004223958,0.00008715569,0.0001272628,0.06319159,0.000387643,0.8684855,0.009032718,0.05787051],"study_design_scores_gemma":[0.00001573134,0.00005626295,0.0001759481,0.0002521579,0.0000137482,0.0001176252,0.00004502268,0.07539059,0.0001934687,0.8345936,0.08911991,0.00002586744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00249741,0.05638158,0.8620477,0.008358154,0.001822614,0.00008463799,0.0003586173,0.0003024391,0.06814679],"genre_scores_gemma":[0.3673995,0.1279865,0.4381875,0.004821713,0.008632204,0.001237805,0.0005955296,0.0004144458,0.05072474],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008191749,"threshold_uncertainty_score":0.02740407,"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."}}