{"id":"W4301342375","doi":"10.48550/arxiv.1503.02244","title":"Asymptotic Optimality of Finite Approximations to Markov Decision\\n Processes with Borel Spaces","year":2015,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Mathematics; State space; Convergence (economics); Applied mathematics; Action (physics); Mathematical optimization; Markov chain; Space (punctuation); Class (philosophy); Markov process; Q-learning; Finite state; Rate of convergence; Average cost; Reinforcement learning; Computer science; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001147579,0.0007445837,0.0009539735,0.0007239518,0.0003972405,0.0003895378,0.003234926,0.0003420898,0.00007951835],"category_scores_gemma":[0.001301132,0.0007300048,0.0002184882,0.003729233,0.0003987159,0.0007269453,0.002846572,0.0009584244,0.0001290945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002247597,"about_ca_system_score_gemma":0.002303634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004770229,"about_ca_topic_score_gemma":0.0001625729,"domain_scores_codex":[0.9956381,0.0003700296,0.0006105357,0.002183425,0.0004880834,0.0007098218],"domain_scores_gemma":[0.9928521,0.001166172,0.0009247775,0.00218906,0.002113496,0.0007544212],"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":[0.0002611344,0.000430746,0.007578641,0.0006680574,0.0001739369,0.0001250786,0.001641377,0.9738873,0.000002290165,0.01160674,0.0001903999,0.003434327],"study_design_scores_gemma":[0.001098947,0.000709926,0.003845903,0.001317395,0.0002379836,0.0000168808,0.0004579786,0.9790555,0.00005165333,0.01144407,0.0007411742,0.001022619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.194803,0.00009295648,0.8001006,0.0002571448,0.0003390282,0.0006556138,0.0000663299,0.0001487794,0.003536501],"genre_scores_gemma":[0.884978,0.0001514504,0.1123464,0.00005991719,0.00008804675,0.000003361438,0.0000229538,0.00003737259,0.002312534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.690175,"threshold_uncertainty_score":0.9995151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05481596787929066,"score_gpt":0.2097878608282766,"score_spread":0.1549718929489859,"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."}}