{"id":"W2064585452","doi":"10.1109/allerton.2013.6736508","title":"Approximation of stationary control policies by quantized control in Markov decision processes","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Markov decision process; Control (management); Markov chain; Markov process; Computer science; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Statistics","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":[0.0001220663,0.0001366699,0.0002916755,0.0001578699,0.00001883789,0.00002701979,0.00009542948,0.00007170373,0.00007245142],"category_scores_gemma":[0.0002268894,0.0001236472,0.00002495907,0.00028037,0.00002010057,0.0006253586,0.000005220585,0.00005618239,0.00001838222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005754407,"about_ca_system_score_gemma":0.00001962598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001511044,"about_ca_topic_score_gemma":0.0000392006,"domain_scores_codex":[0.9989504,0.00003471952,0.0005151532,0.0001251959,0.0001905517,0.0001840402],"domain_scores_gemma":[0.9991015,0.0003915811,0.00009571961,0.0001333654,0.0002397767,0.00003812364],"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":[0.0001278504,0.00007463964,0.005249464,0.0003431251,0.00005420898,3.996519e-7,0.0002893163,0.9089773,0.06761137,0.0007836504,0.002800826,0.01368789],"study_design_scores_gemma":[0.004134448,0.00003062003,0.002682362,0.00006177133,0.000008717855,0.000001145509,0.000157534,0.990391,0.001257547,0.0009873552,0.0001272247,0.0001603273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04573416,0.0005584057,0.9511113,0.00009919266,0.00005924788,0.001031862,0.00002720067,0.0001658015,0.001212843],"genre_scores_gemma":[0.9896547,0.00004674858,0.009833021,0.00006076896,0.00001604116,0.0002656291,0.00002685048,0.00002597726,0.00007025179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9439206,"threshold_uncertainty_score":0.5042186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003127747393292042,"score_gpt":0.201596103838685,"score_spread":0.1984683564453929,"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."}}