{"id":"W2008768326","doi":"10.1023/b:jotp.0000011995.28536.ef","title":"Continuity of the Value of Competitive Markov Decision Processes","year":2003,"lang":"en","type":"article","venue":"Journal of Theoretical Probability","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Mathematics; Markov decision process; Markov chain; Upper and lower bounds; Markov process; Markov kernel; Discounting; Value (mathematics); Mathematical optimization; Partially observable Markov decision process; Space (punctuation); Bellman equation; Function (biology); Markov model; Mathematical economics; Statistics; Variable-order Markov model; Computer science; Mathematical analysis; Economics","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":[0.004969254,0.0006409134,0.001497575,0.001278757,0.0009859354,0.003921583,0.002027475,0.002188517,0.006535301],"category_scores_gemma":[0.03596655,0.000859737,0.0009239078,0.001006067,0.00372676,0.006243883,0.001972456,0.003387258,0.0003965415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002726523,"about_ca_system_score_gemma":0.001683275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002095006,"about_ca_topic_score_gemma":0.001098128,"domain_scores_codex":[0.9977436,0.001049331,0.0001002398,0.0003166715,0.0004431394,0.0003469444],"domain_scores_gemma":[0.966453,0.02829402,0.001352515,0.000919189,0.001386731,0.001594472],"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":[0.0001029222,0.00003500745,0.0004514025,0.00005557702,0.00002292694,0.00006705512,0.000126099,0.02619076,0.0003818664,0.9668756,0.0004995339,0.005191265],"study_design_scores_gemma":[0.00003117146,0.00003450656,0.0002407603,0.00002308302,0.00001108605,0.00003808234,0.00003386974,0.1512411,0.0001929151,0.8474592,0.0006793367,0.00001482598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3059752,0.002150706,0.6335737,0.005242815,0.0001755444,0.0001021642,0.000398732,0.000235409,0.05214588],"genre_scores_gemma":[0.9722325,0.0007461302,0.020497,0.0001704681,0.0001149898,0.00007870825,0.0001003475,0.00004614944,0.006013715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006535301,"threshold_uncertainty_score":0.02628022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008738568404383095,"score_gpt":0.247020988068592,"score_spread":0.2382824196642089,"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."}}