{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001715817,0.0006665508,0.001118095,0.0004340781,0.000397035,0.001295658,0.0009392783,0.0009778845,0.001595111],"category_scores_gemma":[0.00783893,0.0004748343,0.0005208374,0.0006219415,0.001938605,0.001522368,0.001078607,0.00148066,0.0001414777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001612154,"about_ca_system_score_gemma":0.001346937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00836359,"about_ca_topic_score_gemma":0.003122818,"domain_scores_codex":[0.999105,0.000362669,0.00004243762,0.0001417252,0.000204906,0.0001432785],"domain_scores_gemma":[0.9967601,0.00243421,0.0003757423,0.0001429667,0.0002054665,0.00008156104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004467707,0.00001473413,0.0001897947,0.00003949041,0.00001099922,0.00003463453,0.00004327121,0.9423053,0.0004257097,0.0527398,0.0001720976,0.003979452],"study_design_scores_gemma":[0.000005720133,0.0000113676,0.00002477666,0.000004494393,0.00000225916,0.000003210118,0.000003979257,0.9862034,0.0001365341,0.01352513,0.00007583964,0.000003240672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03913145,0.0004421031,0.9579594,0.0003123326,0.0000412267,0.0000283143,0.00005984234,0.0001134714,0.001911817],"genre_scores_gemma":[0.9559941,0.0006707344,0.04114844,0.00009113845,0.00004252927,0.00008371018,0.00009974237,0.00003378631,0.001835999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00836359,"threshold_uncertainty_score":0.01662987,"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."}}