{"id":"W1611140369","doi":"10.48550/arxiv.1310.5770","title":"Quantized Stationary Control Policies in Markov Decision Processes","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Optimal control; Mathematical optimization; Discretization; Partially observable Markov decision process; Stochastic control; Controller (irrigation); Computer science; Markov chain; Computation; Class (philosophy); State (computer science); Markov process; Action (physics); Mathematics; Control (management); Control theory (sociology); Algorithm; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001109705,0.0003194142,0.000444283,0.0004275705,0.00004818113,0.00005277962,0.0003730738,0.0002846032,0.00004714162],"category_scores_gemma":[0.0001356798,0.0003800164,0.0000776353,0.0004903337,0.00004233675,0.0003951098,0.0001262445,0.0003525678,0.00006601663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003400889,"about_ca_system_score_gemma":0.00009794404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002092009,"about_ca_topic_score_gemma":0.0002133828,"domain_scores_codex":[0.9987417,0.00006643576,0.0003311489,0.00046409,0.00008650679,0.000310155],"domain_scores_gemma":[0.9988131,0.0003117795,0.0001453744,0.0004222998,0.0002198028,0.00008762816],"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":[0.00007372255,0.00002161093,0.003337789,0.0002595826,0.0000531526,0.00003336774,0.0001015111,0.9936738,0.00006530601,0.001869181,0.0001447608,0.0003661935],"study_design_scores_gemma":[0.001827448,0.00001500085,0.003342632,0.0002934025,0.00004176594,0.000001714747,0.0001310674,0.9825597,0.00002075658,0.0111576,0.0001836604,0.000425204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3659344,0.0004129639,0.6309877,0.00001738429,0.0003240069,0.0007473276,0.00004829494,0.0003576838,0.001170248],"genre_scores_gemma":[0.9973401,0.0006279372,0.001515109,0.00002279535,0.00005943371,0.00001219367,0.00005113848,0.00005485968,0.0003164526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6314057,"threshold_uncertainty_score":0.9998652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02609860609004199,"score_gpt":0.1765755757086314,"score_spread":0.1504769696185894,"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."}}