{"id":"W2970483889","doi":"10.48550/arxiv.1911.04448","title":"Real-Time Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Open Philanthropy Project","keywords":"Reinforcement learning; Markov decision process; Computer science; Action selection; Computation; Artificial intelligence; State (computer science); Action (physics); Markov process; Mathematical optimization; Machine learning; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009827981,0.0004177019,0.0004330753,0.0004689263,0.00027988,0.0004979157,0.001773053,0.0002603341,0.0002739615],"category_scores_gemma":[0.0001704447,0.000431828,0.0002062134,0.0007823051,0.00005222639,0.000980844,0.0008966241,0.0006903757,0.001584189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005797642,"about_ca_system_score_gemma":0.0002528518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001626293,"about_ca_topic_score_gemma":0.00001769256,"domain_scores_codex":[0.9966118,0.0001784606,0.000643055,0.0006898814,0.0007965804,0.00108023],"domain_scores_gemma":[0.9972275,0.0001885344,0.0003945123,0.001708417,0.0001482395,0.0003328157],"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":[0.00001767507,0.00003063608,0.0124736,0.00002716136,0.00003973108,0.00002637773,0.0002993151,0.9031694,0.01890051,0.06075111,0.001301031,0.002963435],"study_design_scores_gemma":[0.000483428,0.0003704877,0.005305356,0.00005764071,0.000011544,0.00004752182,0.00002963629,0.9802313,0.004935503,0.0003358562,0.007673186,0.0005185789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02635805,0.00006339861,0.9455719,0.001215134,0.0002376212,0.0007886299,6.233034e-7,0.002104313,0.02366031],"genre_scores_gemma":[0.7640935,0.000204196,0.1884339,0.001108562,0.000105837,0.0001520211,0.00002538532,0.00008140918,0.04579527],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7571381,"threshold_uncertainty_score":0.9998134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008090322237890085,"score_gpt":0.2214901116315436,"score_spread":0.2133997893936535,"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."}}