{"id":"W2963437270","doi":"","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates.","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Control variates; Temporal difference learning; Reinforcement learning; Variance (accounting); Computer science; Control (management); Variance reduction; Monte Carlo method; Artificial intelligence; Machine learning; Statistics; Mathematics; Hybrid Monte Carlo; Bayesian probability; Markov chain Monte Carlo","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"],"consensus_categories":[],"category_scores_codex":[0.0009206544,0.0003613908,0.0003918751,0.0003060785,0.0003176255,0.000430544,0.001517513,0.0001554478,0.000154445],"category_scores_gemma":[0.0006751445,0.0002985132,0.00007638901,0.0009073229,0.0004176887,0.000399269,0.0002760147,0.0006631381,0.0006328687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001877362,"about_ca_system_score_gemma":0.000176204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001161549,"about_ca_topic_score_gemma":0.001275252,"domain_scores_codex":[0.996689,0.0002348403,0.000788948,0.0008340014,0.000687497,0.0007657619],"domain_scores_gemma":[0.9977039,0.000656042,0.0002894164,0.0007735165,0.0004007421,0.0001764355],"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":[0.0001677929,0.0001148146,0.009597239,0.000008790043,0.00001747183,0.00003204838,0.002219321,0.83322,0.0006661323,0.02269942,0.00001076672,0.1312462],"study_design_scores_gemma":[0.000216,0.0007720465,0.001982333,0.0001293162,0.000007377871,0.00001093256,0.000368892,0.992449,0.001145028,0.001942318,0.0005660027,0.0004107658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02428019,0.0000232633,0.973681,0.000296254,0.0005485174,0.0004097868,0.000001129842,0.0002514954,0.0005083972],"genre_scores_gemma":[0.9147429,0.000009434812,0.08444803,0.0002378197,0.0001397444,0.00002624314,0.000003935175,0.00002242893,0.0003694391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8904628,"threshold_uncertainty_score":0.9999467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04175902341515242,"score_gpt":0.2973694407687176,"score_spread":0.2556104173535652,"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."}}