{"id":"W4405644932","doi":"10.3233/fun-2006-712-310","title":"Reinforcement Learning with Approximation Spaces","year":2006,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Mathematics; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003365096,0.001109556,0.001534832,0.000683462,0.0004477375,0.001713375,0.001584162,0.001323917,0.00260134],"category_scores_gemma":[0.0108511,0.0004022813,0.0009909661,0.0006734062,0.002084007,0.001970162,0.001867015,0.002282951,0.0003739345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001611748,"about_ca_system_score_gemma":0.001095765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002351146,"about_ca_topic_score_gemma":0.001451193,"domain_scores_codex":[0.9976164,0.00132013,0.0001209457,0.0002651652,0.0005367345,0.0001407098],"domain_scores_gemma":[0.9946082,0.00400992,0.0003714943,0.0004038583,0.0004175708,0.0001889484],"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":[0.00009449006,0.00006826509,0.0005869644,0.0001547589,0.00009829104,0.00006860343,0.0001532294,0.7401604,0.0006032428,0.2140011,0.0006918901,0.04331873],"study_design_scores_gemma":[0.00002487826,0.00006507002,0.00005871353,0.00001545193,0.00001016523,0.00001627915,0.00001279931,0.9232623,0.0002109039,0.0750137,0.001301017,0.000008798825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006850131,0.0005333083,0.9891722,0.0002925394,0.00005644238,0.00004223712,0.0000201269,0.0001117698,0.002921218],"genre_scores_gemma":[0.707848,0.001144207,0.2847809,0.0002358625,0.0002034771,0.0003927652,0.0001151476,0.00006528118,0.005214273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003365096,"threshold_uncertainty_score":0.01779658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008276264063803971,"score_gpt":0.2087067039831487,"score_spread":0.2004304399193447,"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."}}