{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003175053,0.0001142203,0.0003758856,0.00004575066,0.00005101066,0.00002968021,0.001200905,0.00006985619,0.00005032332],"category_scores_gemma":[0.01288898,0.00006595083,0.0002072392,0.0004198441,0.001033645,0.0002038475,0.0002435035,0.0003290049,0.000001099632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006281619,"about_ca_system_score_gemma":0.0003461613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.078832e-7,"about_ca_topic_score_gemma":5.034146e-7,"domain_scores_codex":[0.997416,0.000592139,0.000902623,0.0001530351,0.0007625936,0.0001736636],"domain_scores_gemma":[0.9956352,0.001716231,0.0008723274,0.0005518672,0.001144638,0.00007975174],"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":[0.00006397497,0.0001510034,0.0106288,0.0001177235,0.00002277158,0.000001000899,0.0002498324,0.0132679,0.0002037966,0.9745712,0.00001782811,0.0007042057],"study_design_scores_gemma":[0.0006045145,0.0005098988,0.01526971,0.0003467049,0.00003850878,0.00004524945,0.00005109856,0.006670096,0.03016278,0.9460148,0.0001747261,0.0001119075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2001693,0.00005468338,0.7928119,0.0002699734,0.0002907532,0.0002104023,0.000001107823,0.000006357884,0.006185557],"genre_scores_gemma":[0.9237328,0.000007237967,0.07619293,0.00003878019,0.00001281799,6.317566e-7,3.800623e-8,0.000004015749,0.00001076998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7235635,"threshold_uncertainty_score":0.9954259,"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."}}