{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005357964,0.0001913828,0.0001593563,0.0005425121,0.0002156908,0.0006093734,0.0003736845,0.0001191019,0.00007740433],"category_scores_gemma":[0.0004760102,0.0001753225,0.00004805387,0.0007788932,0.00003716104,0.001482356,0.0001200825,0.0001475521,0.0001969798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001526477,"about_ca_system_score_gemma":0.00006460094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005067438,"about_ca_topic_score_gemma":0.000004775511,"domain_scores_codex":[0.9983137,0.0002995621,0.0003027454,0.000483463,0.0003048265,0.0002956789],"domain_scores_gemma":[0.9989625,0.0001395977,0.0001200886,0.0005523882,0.00008105893,0.0001443636],"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":[0.000006507533,0.000040674,0.000006117706,0.000004488879,0.000005437708,0.000001381463,0.001223152,0.0001032409,0.001951186,0.6179425,0.001444146,0.3772712],"study_design_scores_gemma":[0.000564164,0.0004082967,0.0007150155,0.00001410819,0.000004675353,0.0000953203,0.00001431169,0.9498676,0.01541946,0.01962603,0.01296864,0.0003023464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002533906,0.00003330127,0.9626981,0.009905772,0.0002448106,0.0002530651,0.000002331123,0.000215739,0.02411298],"genre_scores_gemma":[0.06430928,0.00003868956,0.9251498,0.004204446,0.0007468318,0.00003363749,0.000005193412,0.00001572508,0.005496383],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9497644,"threshold_uncertainty_score":0.7149444,"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."}}