{"id":"W4382141796","doi":"10.48550/arxiv.2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Age of Information Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Discounting; Distribution (mathematics); Variance (accounting); Applied mathematics; Mathematical optimization; Mathematics; Computer science; Statistics; Mathematical analysis; Economics; Finance","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000532693,0.0003606956,0.0003623665,0.001807961,0.0001642036,0.0002367978,0.001836009,0.0002793059,0.00001398348],"category_scores_gemma":[0.0004935062,0.0004167311,0.0001734153,0.002465417,0.00006479893,0.0007769654,0.001929787,0.0006868049,0.0002231155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001282926,"about_ca_system_score_gemma":0.0006408466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001704594,"about_ca_topic_score_gemma":0.0001069589,"domain_scores_codex":[0.9978211,0.0002827482,0.0003954159,0.0008548668,0.000152803,0.0004930645],"domain_scores_gemma":[0.9977078,0.0003217447,0.0004593436,0.001189736,0.000147249,0.0001741398],"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":[0.00001097307,0.00004515158,0.0007136186,0.00005300926,0.00002714145,0.00006159677,0.002335017,0.8429651,0.000002750297,0.1473172,0.0001574735,0.006311024],"study_design_scores_gemma":[0.0003834874,0.00003860555,0.002595488,0.0001734669,0.000008024414,0.000006078455,0.0002627374,0.9695925,0.0001548471,0.02610751,0.0001961801,0.0004810614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04028386,0.000005446849,0.9520125,0.0008421348,0.001029534,0.0003889651,0.00001532954,0.0004916146,0.004930582],"genre_scores_gemma":[0.9622512,0.0001101262,0.03327549,0.0003668721,0.0002100622,0.000003805138,0.00003319068,0.00003878508,0.003710425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9219674,"threshold_uncertainty_score":0.9998285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1144003186648897,"score_gpt":0.2718175409360546,"score_spread":0.1574172222711649,"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."}}