{"id":"W2120045945","doi":"10.1287/moor.2016.0832","title":"On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces","year":2017,"lang":"en","type":"preprint","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"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; Mathematical optimization; Action (physics); Markov chain; Space (punctuation); Finite state; Markov process; Class (philosophy); Q-learning; State (computer science); Average cost; Reinforcement learning; Computer science; Algorithm; 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":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003258283,0.0002377527,0.0004257304,0.0005130506,0.0006890981,0.001133866,0.003825783,0.0001368816,0.00003621844],"category_scores_gemma":[0.01438981,0.0001499062,0.00007118355,0.0006598789,0.0003633832,0.0002568683,0.002433891,0.0007571104,0.00004305261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007494747,"about_ca_system_score_gemma":0.001283344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005982395,"about_ca_topic_score_gemma":0.00006126883,"domain_scores_codex":[0.9963108,0.0002126725,0.0006637246,0.000459486,0.002018863,0.0003344549],"domain_scores_gemma":[0.9892951,0.004460787,0.0002822295,0.003223976,0.002640357,0.00009752711],"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":[0.00001011818,0.0001787525,0.00001894738,0.0009360077,0.00004856374,0.00000109173,0.002900616,0.8835837,0.0000394749,0.1117399,0.000353363,0.000189464],"study_design_scores_gemma":[0.000139972,0.0003584295,0.0001359395,0.002429406,0.00001612565,0.000002048526,0.0002748581,0.9816242,0.001750771,0.01304853,0.00003128037,0.0001884222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02780928,0.00002795787,0.9619757,0.002293595,0.00005710416,0.001723886,0.00002330539,0.00003183457,0.00605736],"genre_scores_gemma":[0.4876454,0.00004192169,0.5111964,0.00001337424,0.00001625764,0.0002441033,0.00001075127,0.00001981911,0.000811999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4598361,"threshold_uncertainty_score":0.999903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1148588961374406,"score_gpt":0.3944555419249472,"score_spread":0.2795966457875066,"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."}}