{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204387,0.0009662736,0.001436516,0.0006335531,0.0003440098,0.00155893,0.001579559,0.001131249,0.006449401],"category_scores_gemma":[0.005444049,0.0006843468,0.001006051,0.001010059,0.001470247,0.001696654,0.0009265154,0.002961016,0.001256146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001859941,"about_ca_system_score_gemma":0.001335554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005966555,"about_ca_topic_score_gemma":0.003968943,"domain_scores_codex":[0.9993351,0.0002728846,0.00002452355,0.00008767058,0.0002320042,0.00004778647],"domain_scores_gemma":[0.9969667,0.002535588,0.0001015715,0.0001618256,0.0001701087,0.00006420615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002087424,0.00002995866,0.0001817229,0.0001007137,0.00002946332,0.0000289954,0.00005589424,0.2126117,0.0002223543,0.7570964,0.003666767,0.02595518],"study_design_scores_gemma":[0.000005808481,0.000005343373,0.00006339295,0.00003230143,0.000005351145,0.00001241062,0.000005984294,0.5373732,0.00008317658,0.4592999,0.003105794,0.000007263267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003513226,0.002963977,0.9747105,0.0005880888,0.0001843926,0.00001594285,0.000149353,0.0002053125,0.01766931],"genre_scores_gemma":[0.5240186,0.01287224,0.4029759,0.0004755894,0.0009464988,0.0003419921,0.001353982,0.0004334576,0.0565817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006449401,"threshold_uncertainty_score":0.02157539,"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."}}