{"id":"W2077559824","doi":"10.1287/opre.1090.0705","title":"Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes","year":2009,"lang":"en","type":"article","venue":"Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"GAVI Alliance","keywords":"Markov decision process; Monotone polygon; Mathematical optimization; Algorithm; Convergence (economics); Markov chain; Operator (biology); Mathematics; Computer science; Dynamic programming; Contraction (grammar); Acceleration; Linear programming; 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":[0.003652947,0.001135856,0.001059004,0.000579718,0.0004692837,0.0009886138,0.001234837,0.001211669,0.002225137],"category_scores_gemma":[0.01109842,0.0004779153,0.001004724,0.0007437366,0.002026681,0.002043204,0.001878821,0.002775327,0.0004497109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007192646,"about_ca_system_score_gemma":0.001408159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001118266,"about_ca_topic_score_gemma":0.0006488925,"domain_scores_codex":[0.9987244,0.0006695715,0.0000560521,0.0001427137,0.0003073507,0.00009981072],"domain_scores_gemma":[0.9956211,0.003519722,0.0002101698,0.0002005735,0.0003220562,0.0001263838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001354189,0.0001055288,0.0005442976,0.0002212485,0.0000540094,0.00009641162,0.0002727772,0.4460562,0.003208662,0.4630357,0.001375968,0.08489369],"study_design_scores_gemma":[0.00001722229,0.00006335796,0.00003269868,0.00001661921,0.000006343411,0.00002346036,0.000008085284,0.9199017,0.0007625404,0.07810619,0.001052979,0.000008685378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006001553,0.0002549849,0.9922057,0.0001365468,0.00004560379,0.0000332683,0.00000590451,0.00006311559,0.001253296],"genre_scores_gemma":[0.3414166,0.00110044,0.6517525,0.0002156697,0.000192628,0.0004586191,0.00005311236,0.0001364441,0.004674017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003652947,"threshold_uncertainty_score":0.01931888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.108226386416609,"score_gpt":0.4288051744627904,"score_spread":0.3205787880461814,"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."}}