{"id":"W2998102890","doi":"10.1109/tac.2019.2907172","title":"Asymptotic Optimality of Finite Model Approximations for Partially Observed Markov Decision Processes With Discounted Cost","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Partially observable Markov decision process; Mathematics; Finite state; Mathematical optimization; Markov process; State space; Applied mathematics; Finite set; Markov chain; Quantization (signal processing); Markov kernel; Space (punctuation); Markov model; Variable-order Markov model; Computer science; Algorithm; Mathematical analysis; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001911116,0.0002739289,0.0005197467,0.0001574597,0.00008975026,0.00004470366,0.0001725242,0.000102553,0.00004728787],"category_scores_gemma":[0.00006251725,0.0002391679,0.0001117878,0.0003491781,0.00003554157,0.0004193919,6.168315e-7,0.00009892397,0.00001402819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192789,"about_ca_system_score_gemma":0.0001400844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004311282,"about_ca_topic_score_gemma":0.0001112437,"domain_scores_codex":[0.9984591,0.0000343487,0.0006476853,0.0002664639,0.0003021621,0.0002902635],"domain_scores_gemma":[0.9978823,0.001123782,0.0001699675,0.0004421289,0.0003022093,0.00007961755],"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":[0.0002281508,0.0001153352,0.00002004156,0.0008290458,0.0001606073,2.447959e-7,0.0001258572,0.9909481,0.001398973,0.00004080244,0.000005433508,0.006127364],"study_design_scores_gemma":[0.004627245,0.0001600063,0.00007453365,0.000393111,0.0001683986,0.000002324113,0.00004487305,0.9927414,0.001394293,0.0001335932,0.000009227068,0.0002509919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02176052,0.00003233875,0.9738087,0.0000444343,0.0001822832,0.003313265,0.0003010327,0.0004351462,0.0001222483],"genre_scores_gemma":[0.938085,0.000009122594,0.0604189,0.00002378095,0.00001088546,0.001256837,0.00001405301,0.00006623042,0.0001152247],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9163244,"threshold_uncertainty_score":0.9752986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01354082472989133,"score_gpt":0.2283057213937988,"score_spread":0.2147648966639075,"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."}}