{"id":"W2800446008","doi":"10.1007/978-3-319-79033-6_3","title":"Finite-Action Approximation of Markov Decision Processes","year":2018,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Markov decision process; Control theory (sociology); Controller (irrigation); Actuator; Computer science; Markov chain; Partially observable Markov decision process; Optimal control; Discretization; Quantization (signal processing); Markov process; Transmission (telecommunications); Mathematical optimization; Mathematics; Markov model; Control (management); Algorithm; Artificial intelligence; Telecommunications","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001499428,0.0004382756,0.001143891,0.0002694818,0.00007579674,0.0000558518,0.0002432234,0.000613765,0.0001478725],"category_scores_gemma":[0.001749068,0.0003683693,0.0002423302,0.00005755352,0.0000817904,0.0001096792,0.00004236611,0.0002390887,0.000003443655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001172745,"about_ca_system_score_gemma":0.00016644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002231759,"about_ca_topic_score_gemma":0.00005110593,"domain_scores_codex":[0.9974498,0.0001274964,0.00112049,0.0004451935,0.0006203583,0.0002366475],"domain_scores_gemma":[0.9945714,0.002121059,0.001429455,0.0007181175,0.001069154,0.00009080996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003399487,0.000471222,0.0000635691,0.067021,0.002873004,0.00006665465,0.003123078,0.0001188646,0.002876886,0.6321645,0.1079362,0.1798855],"study_design_scores_gemma":[0.00703909,0.001240124,0.000005623747,0.0158567,0.001885476,0.0001021567,0.0006275517,0.01840476,0.0008286674,0.1411399,0.8105057,0.002364225],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0002794122,0.002222919,0.5905949,0.00002395807,0.002064206,0.002575112,0.0002269979,0.0001627203,0.4018497],"genre_scores_gemma":[0.1563294,0.0004828809,0.02882873,0.00007231122,0.003487066,0.0004519481,0.0001194584,0.0004361847,0.809792],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7025695,"threshold_uncertainty_score":0.9998768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07599065223292019,"score_gpt":0.3337092000526165,"score_spread":0.2577185478196963,"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."}}