{"id":"W3213853783","doi":"","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Convexity; Truncation (statistics); Variance (accounting); Convergence (economics); Mathematics; Term (time); Variance reduction; Reinforcement learning; Applied mathematics; Mathematical optimization; Function (biology); Distribution (mathematics); Computer science; Combinatorics; Statistics; Mathematical analysis; Physics; Economics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0002677781,0.0001046726,0.0001288029,0.00009190254,0.000153243,0.00003472375,0.0006321308,0.00003769444,0.00003785223],"category_scores_gemma":[0.0004907795,0.00009158714,0.00005576337,0.001074511,0.0001109319,0.0001464092,0.0003256863,0.0001234136,0.00001398152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005132774,"about_ca_system_score_gemma":0.0001547972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001103417,"about_ca_topic_score_gemma":0.000002869662,"domain_scores_codex":[0.9990231,0.0001738215,0.0001208387,0.0003768013,0.00009224433,0.0002132409],"domain_scores_gemma":[0.9982222,0.0008631718,0.0001143451,0.0006201999,0.0001069321,0.00007316351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003387957,0.00001805782,0.0002848285,0.000005782834,0.0000123311,0.00001449506,0.0002253606,0.3619614,0.0005540926,0.6367816,0.0000284764,0.0001102322],"study_design_scores_gemma":[0.000282894,0.0001105913,0.00125646,0.00002356821,0.00001476412,0.000006810903,0.000117213,0.967151,0.006996054,0.02357899,0.0003183738,0.0001432117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1015284,0.00001012605,0.8961877,0.0003814244,0.0001329559,0.00007586159,0.000001593423,0.00003280737,0.001649227],"genre_scores_gemma":[0.9882666,0.00004670539,0.01070771,0.0002234487,0.00001317434,2.064029e-7,6.286459e-7,0.000004374575,0.0007370909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8867383,"threshold_uncertainty_score":0.3734815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05728126830244275,"score_gpt":0.2121414442744954,"score_spread":0.1548601759720526,"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."}}