{"id":"W2012728920","doi":"10.5555/777092.777137","title":"On policy iteration as a Newton's method and polynomial policy iteration algorithms","year":2002,"lang":"en","type":"article","venue":"","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov decision process; Mathematics; Power iteration; Upper and lower bounds; Mathematical optimization; Dynamic programming; Time complexity; Polynomial; Linear programming; Newton's method; Iterative method; Combinatorics; Discrete mathematics; Markov process","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":[0.004132353,0.002044752,0.001790581,0.001419431,0.001035599,0.001831386,0.001645866,0.00203091,0.006596502],"category_scores_gemma":[0.0208699,0.001050577,0.001764172,0.002152536,0.004930559,0.004333748,0.002760591,0.005821836,0.00193456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00307929,"about_ca_system_score_gemma":0.003409048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007410733,"about_ca_topic_score_gemma":0.005015847,"domain_scores_codex":[0.9962922,0.001583215,0.0001236778,0.0005248801,0.001125211,0.0003508614],"domain_scores_gemma":[0.9843126,0.01295875,0.000623136,0.0008981052,0.0009839422,0.0002234836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001446646,0.00006058214,0.0004323593,0.000184746,0.00004232232,0.00006499435,0.000161278,0.5040686,0.00108491,0.4261111,0.00292812,0.06471634],"study_design_scores_gemma":[0.00002196859,0.00002699486,0.00006419952,0.00003185547,0.00001004024,0.00002551061,0.000008974338,0.8365471,0.0005075716,0.1592363,0.003504543,0.00001494899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001816979,0.0006052941,0.9912298,0.0003450518,0.00006349468,0.00003459808,0.00002509158,0.000230904,0.00564886],"genre_scores_gemma":[0.2229401,0.002902269,0.7608838,0.0004646518,0.0004262148,0.0004489877,0.0001852766,0.0007057317,0.01104292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007410733,"threshold_uncertainty_score":0.02234197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02613547373007506,"score_gpt":0.338646164684744,"score_spread":0.3125106909546689,"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."}}