{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002856444,0.0001128019,0.0001025236,0.0003678615,0.0009367064,0.002253033,0.001144011,0.00007619266,0.00001343368],"category_scores_gemma":[0.001455059,0.00008164677,0.00002917321,0.00176281,0.00003673348,0.001546361,0.00008199775,0.0003149586,0.00003683981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001134862,"about_ca_system_score_gemma":0.0003894376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002889127,"about_ca_topic_score_gemma":0.00007713408,"domain_scores_codex":[0.9977187,0.0003241357,0.0003447509,0.0003712643,0.0008663686,0.0003747654],"domain_scores_gemma":[0.9979531,0.0005994122,0.00001926682,0.0005584999,0.0008290804,0.0000406373],"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":[0.00001202644,0.00009530191,0.00006697046,0.00001316979,0.0000030627,0.000002884918,0.002638784,0.8975767,0.0008549906,0.04675812,0.002339049,0.0496389],"study_design_scores_gemma":[0.0003521733,0.0003564,0.001113622,0.00003624613,0.000001275559,0.000005072714,0.0001570541,0.9922379,0.001268587,0.000779286,0.003583279,0.000109095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009757719,0.0000673095,0.9818187,0.005770266,0.0001057727,0.001287026,0.000001511988,0.0000402798,0.001151445],"genre_scores_gemma":[0.8128249,0.00008020664,0.1850961,0.0007144877,0.0001612422,0.000330183,0.00004814017,0.000008973081,0.0007358346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8030671,"threshold_uncertainty_score":0.9987827,"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."}}