{"id":"W2135097260","doi":"10.1007/3-540-44886-1_26","title":"Model-Based Least-Squares Policy Evaluation","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Estimator; Computation; Least-squares function approximation; Basis (linear algebra); Algorithm; Set (abstract data type); Markov decision process; Mathematical optimization; Markov process; Mathematics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001903856,0.0006310703,0.0004931221,0.00161223,0.0003314812,0.0007679187,0.003580198,0.0003874902,0.00003834118],"category_scores_gemma":[0.0004337212,0.0006154762,0.0001685191,0.0009622765,0.0006028542,0.000673201,0.0006955024,0.0009059838,0.00009933289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047089,"about_ca_system_score_gemma":0.00297138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001418567,"about_ca_topic_score_gemma":0.00001352231,"domain_scores_codex":[0.9943141,0.00009159766,0.0006386798,0.001584598,0.002521795,0.0008492799],"domain_scores_gemma":[0.996359,0.0003345625,0.0004353857,0.002028227,0.0006291032,0.0002137595],"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":[0.000001897763,0.000009470249,0.00001313317,0.00001943277,0.000004860571,0.000007220835,0.0001744186,0.8183084,0.00002487601,0.02077237,0.00002785138,0.1606361],"study_design_scores_gemma":[0.0003336653,0.0001315108,0.00001557587,0.0001978969,0.0000113318,0.00001251821,4.71722e-8,0.9155234,0.0003394191,0.08215408,0.0006978613,0.0005827551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000110338,0.0001890869,0.9850875,0.001661354,0.001110508,0.0006380625,0.00000184221,0.000191007,0.01110964],"genre_scores_gemma":[0.2200319,0.00002085961,0.770826,0.007254215,0.0004949348,0.00002847157,0.00001529779,0.00007542592,0.001252823],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2200209,"threshold_uncertainty_score":0.9996297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03695932473739669,"score_gpt":0.2924345026014347,"score_spread":0.255475177864038,"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."}}