{"id":"W1787017840","doi":"10.1016/j.jmaa.2015.10.008","title":"Near optimality of quantized policies in stochastic control under weak continuity conditions","year":2015,"lang":"en","type":"preprint","venue":"Journal of Mathematical Analysis and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Discretization; Constructive; Markov process; Mathematical optimization; Optimal control; Stochastic control; Mathematics; Partially observable Markov decision process; Reduction (mathematics); Markov chain; Class (philosophy); Applied mathematics; Computer science; Process (computing); Mathematical analysis","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":[0.001402186,0.0001776585,0.001083842,0.0004156328,0.00006802913,0.000190243,0.0007109049,0.0001360906,0.00002444067],"category_scores_gemma":[0.0002349303,0.0001418709,0.0003596238,0.0007004056,0.0002362854,0.0001196905,0.0003251357,0.0004845263,0.000004705917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006266202,"about_ca_system_score_gemma":0.0002165739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002881575,"about_ca_topic_score_gemma":0.000007897571,"domain_scores_codex":[0.9976266,0.0001409382,0.001349978,0.0002112396,0.0005005657,0.00017067],"domain_scores_gemma":[0.9965993,0.0006146907,0.001468169,0.0005564726,0.0005996744,0.000161681],"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":[0.000005036996,0.0001604941,0.0004563939,0.00006039628,0.0005728402,5.153399e-7,0.0002276215,0.8287039,0.00003327867,0.1696879,0.00003800505,0.0000536115],"study_design_scores_gemma":[0.0005693681,0.0000433716,0.006264738,0.0001043038,0.001140812,0.000009769485,0.0001539728,0.8680326,0.000008679668,0.1234923,0.00003288825,0.0001471325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02226228,0.0001069775,0.9760417,0.0008430688,0.00001420846,0.0002956248,0.00001678381,0.00001207265,0.0004072546],"genre_scores_gemma":[0.9641783,0.00002031691,0.03563575,0.00003735787,0.0000327801,0.00003046489,0.000006430432,0.000006093429,0.00005245218],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.941916,"threshold_uncertainty_score":0.5785327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03001228517212436,"score_gpt":0.3246506552190392,"score_spread":0.2946383700469149,"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."}}