{"id":"W223326216","doi":"10.1613/jair.4301","title":"Policy Iteration Based on Stochastic Factorization","year":2014,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; McGill University; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Markov decision process; Factorization; Mathematical optimization; Factoring; Mathematics; Multiplication (music); Computer science; Markov process; Applied mathematics; Algorithm; Finance","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003478014,0.00009844283,0.0001493787,0.001099391,0.0002275989,0.0004986643,0.0009011704,0.00006964059,0.00002771444],"category_scores_gemma":[0.004259935,0.00008301176,0.00007371903,0.001179662,0.00008377041,0.0004952457,0.00007894828,0.000585157,0.0001444815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001956028,"about_ca_system_score_gemma":0.0003836134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001127986,"about_ca_topic_score_gemma":0.000001530108,"domain_scores_codex":[0.9969166,0.0004562931,0.0005771903,0.0001735324,0.001520447,0.000355969],"domain_scores_gemma":[0.9971175,0.0009934565,0.0002527921,0.0003588338,0.001120819,0.000156568],"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":[0.00002588778,0.00004219426,0.00001801281,0.00000559016,0.000003567186,0.000002458743,0.0002607414,0.8027494,0.001479438,0.1235932,0.00004641026,0.07177306],"study_design_scores_gemma":[0.00002827172,0.001036857,0.00006314416,0.00006494281,0.000001451529,0.000004267699,0.00003438232,0.9617393,0.009555851,0.02721175,0.0001863443,0.00007342894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009982113,0.000003378184,0.9951997,0.002491475,0.0004031405,0.0001093748,1.772307e-7,0.00001899243,0.0007755691],"genre_scores_gemma":[0.9878107,0.000004144689,0.01132944,0.0001192228,0.0006452555,0.000001757418,8.12952e-7,0.000008986704,0.00007964638],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9868125,"threshold_uncertainty_score":0.5099847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.127637866729138,"score_gpt":0.4165855694153244,"score_spread":0.2889477026861863,"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."}}