{"id":"W4297686857","doi":"10.48550/arxiv.1710.07009","title":"Finite Model Approximations for Partially Observed Markov Decision\\n Processes with Discounted Cost","year":2017,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Markov decision process; Partially observable Markov decision process; Finite state; Mathematics; State space; Mathematical optimization; Finite set; Markov process; Applied mathematics; Markov chain; Space (punctuation); Quantization (signal processing); Markov model; Markov kernel; Mathematical economics; Computer science; Variable-order Markov model; Algorithm; Mathematical analysis; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002782597,0.001069145,0.001477826,0.0007910941,0.000532206,0.002550822,0.002200561,0.001664942,0.00228935],"category_scores_gemma":[0.01503638,0.0007295214,0.00141001,0.0007114357,0.002167149,0.002874756,0.001825415,0.002916131,0.0002297565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003947465,"about_ca_system_score_gemma":0.001745233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01332717,"about_ca_topic_score_gemma":0.007888077,"domain_scores_codex":[0.9983029,0.0007076748,0.00007966104,0.0002701365,0.0004504377,0.0001891979],"domain_scores_gemma":[0.9931256,0.005280985,0.0006207413,0.0003346785,0.0003699037,0.0002681955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003961272,0.00001831088,0.0003254424,0.00004704392,0.00002316403,0.00005949609,0.00007966818,0.8322365,0.0001706459,0.1640586,0.0001952708,0.002746338],"study_design_scores_gemma":[0.000003711694,0.000005768842,0.0000213398,0.0000061941,0.000002492073,0.000004206406,0.000005631811,0.9698182,0.00004481018,0.02997363,0.00011098,0.000003124296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03843983,0.000604136,0.9562032,0.000548001,0.00005249663,0.00003739994,0.0001464905,0.0001274869,0.00384104],"genre_scores_gemma":[0.8879253,0.0006531041,0.1063385,0.0001271979,0.00006342339,0.0001962893,0.0003547379,0.00006691751,0.004274698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01332717,"threshold_uncertainty_score":0.02864099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09329733351775947,"score_gpt":0.2073937547559784,"score_spread":0.1140964212382189,"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."}}