{"id":"W2126905415","doi":"10.1287/moor.2014.0704","title":"A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies","year":2015,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Bounded function; Convergence (economics); Mathematical optimization; Bellman equation; Power iteration; Function (biology); Markov decision process; Optimal control; Average cost; Context (archaeology); Value (mathematics); Applied mathematics; Iterative method; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007498272,0.00009925648,0.0002736037,0.0008280907,0.000310529,0.0004519302,0.0002945703,0.00005960629,0.000009951143],"category_scores_gemma":[0.00874678,0.00006767699,0.00003356341,0.001104539,0.0001639976,0.0004372674,0.00005125966,0.00009543439,0.00001042014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006026918,"about_ca_system_score_gemma":0.0007503788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004217918,"about_ca_topic_score_gemma":0.0004146461,"domain_scores_codex":[0.9973286,0.0003822082,0.0004571026,0.0002297103,0.001368332,0.0002340784],"domain_scores_gemma":[0.9939682,0.001817665,0.00008028741,0.0003886475,0.003591456,0.00015372],"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":[0.00009262503,0.0001167035,0.00007589139,0.00001412534,0.0000315377,4.729829e-7,0.007176659,0.6792573,0.0009335354,0.3089528,0.001285589,0.002062715],"study_design_scores_gemma":[0.00112261,0.0003525055,0.00008848798,0.00002473495,0.00001655513,0.00001184169,0.004298586,0.9544473,0.0005833181,0.03864275,0.0003278085,0.00008354407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04411188,0.00004742908,0.9511244,0.002256437,0.00002194543,0.0008736037,0.00004480828,0.00001285483,0.001506689],"genre_scores_gemma":[0.696162,0.00001024486,0.3015015,0.0000228366,0.00004844979,0.00007226328,0.000009126293,0.00001415895,0.00215943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6520501,"threshold_uncertainty_score":0.999603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.33334413430034,"score_gpt":0.500800905692265,"score_spread":0.1674567713919249,"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."}}