{"id":"W4385890042","doi":"10.48550/arxiv.2308.07591","title":"Approximations and Learning for Continuous State and Action MDPs under Average Cost Criteria","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Mathematics; Markov decision process; Discretization; Ergodicity; Mathematical optimization; Applied mathematics; Convergence (economics); Markov process; Computer science; Mathematical analysis","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":[0.005995676,0.001121882,0.001757879,0.0008580487,0.000572935,0.001932698,0.001967744,0.001880978,0.001593283],"category_scores_gemma":[0.02542818,0.0006389107,0.001058453,0.0009165472,0.002934839,0.003487462,0.002598516,0.003114359,0.000242176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00304666,"about_ca_system_score_gemma":0.002066158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005375491,"about_ca_topic_score_gemma":0.002440563,"domain_scores_codex":[0.9971625,0.001196195,0.0001811703,0.0004816033,0.0007790687,0.0001994067],"domain_scores_gemma":[0.9857244,0.01139556,0.0008991368,0.0007423021,0.0008769692,0.0003616927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005807348,0.00002711766,0.0005184149,0.0000970169,0.00003421591,0.00004053093,0.00008862904,0.8855759,0.0004088324,0.1035555,0.0002567249,0.009339091],"study_design_scores_gemma":[0.000005295791,0.00001517039,0.00003736532,0.00000966666,0.000002974619,0.0000073696,0.000006570261,0.9745625,0.0001380846,0.02508757,0.0001239529,0.000003407989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01097414,0.0002708831,0.9873739,0.0002502859,0.00002421381,0.00002829205,0.00003581833,0.00007716296,0.0009652829],"genre_scores_gemma":[0.7471095,0.000638656,0.2487801,0.0002362973,0.00009658821,0.0002910289,0.0002529662,0.0001258249,0.002468772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005995676,"threshold_uncertainty_score":0.03170854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1385473571740192,"score_gpt":0.2429579445238171,"score_spread":0.104410587349798,"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."}}