{"id":"W3193685318","doi":"10.1017/9781108571401.047","title":"Markov Decision Processes","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Markov decision process; Markov chain; Markov process; Mathematics; 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":[0.0007430954,0.0009066137,0.000808787,0.0005870233,0.0004013098,0.001894949,0.0007981969,0.001188946,0.07020324],"category_scores_gemma":[0.003329297,0.0003092124,0.0005178973,0.001179812,0.0006826125,0.001503544,0.0006993348,0.001729896,0.01828193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087654,"about_ca_system_score_gemma":0.0008564763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001895934,"about_ca_topic_score_gemma":0.002459475,"domain_scores_codex":[0.9995616,0.0001542913,0.00002048878,0.00009909026,0.0001209352,0.0000436046],"domain_scores_gemma":[0.9987568,0.0009131573,0.00004930567,0.0001054222,0.0001148109,0.00006059336],"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":[0.00004187793,0.00005356994,0.0005333991,0.0003181774,0.00004599825,0.0001612791,0.00009697932,0.02481367,0.0003509363,0.7604812,0.1138255,0.09927733],"study_design_scores_gemma":[0.00002653319,0.00003737243,0.0005882781,0.0001789301,0.00002365844,0.0001793124,0.0000415365,0.06495872,0.0002430643,0.7579146,0.1757827,0.00002514935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0067253,0.02452197,0.5152758,0.007998793,0.001379505,0.000166059,0.006343684,0.00105465,0.4365343],"genre_scores_gemma":[0.2736124,0.04490488,0.109253,0.002281879,0.001732765,0.000672351,0.009366866,0.0005348194,0.5576411],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07020324,"threshold_uncertainty_score":0.2348533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09019827160613175,"score_gpt":0.318277106807889,"score_spread":0.2280788352017573,"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."}}