{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009789869,0.0001011742,0.00008630443,0.00005278411,0.0002156684,0.0003755696,0.000298026,0.00002127461,0.00003276028],"category_scores_gemma":[0.000002242903,0.00007594528,0.00002320884,0.000273914,0.00003056936,0.0009862207,0.00009911841,0.00009861193,0.0001621458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003638777,"about_ca_system_score_gemma":0.00001763272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003599498,"about_ca_topic_score_gemma":0.000005243744,"domain_scores_codex":[0.9991802,0.000009662685,0.0002421808,0.0001092592,0.0002461458,0.0002125537],"domain_scores_gemma":[0.9994957,0.00002853606,0.000139408,0.0002597607,0.00003233471,0.00004428566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000109417,0.00007663742,0.00198246,0.00006950934,0.000024213,0.000002335555,0.001440609,0.1945301,0.0002692868,0.7649245,0.01043786,0.02623154],"study_design_scores_gemma":[0.0005785234,0.0002201944,0.002359518,0.00004682375,0.000009060373,0.00002241311,0.0002158553,0.8652281,0.001551619,0.002488938,0.1269645,0.000314487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02702228,0.00001185375,0.9261186,0.0009601215,0.00004073188,0.0002989869,3.407889e-7,0.0002285951,0.04531856],"genre_scores_gemma":[0.9612536,0.000004193728,0.03698462,0.000320762,0.00004974787,0.00007265987,0.00002744547,0.000004859728,0.001282101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9342313,"threshold_uncertainty_score":0.3621626,"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."}}