{"id":"W2809487708","doi":"","title":"Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variance (accounting); Temporal difference learning; Computer science; Reinforcement learning; Mean squared error; Lookup table; Function (biology); Algorithm; Artificial intelligence; Statistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053409,0.001083667,0.001183979,0.0009732767,0.0003456267,0.001517429,0.002033551,0.001379444,0.002254158],"category_scores_gemma":[0.03270878,0.0004434911,0.0006960768,0.0006670312,0.00102828,0.002932574,0.002642686,0.002474428,0.0005250929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005549,"about_ca_system_score_gemma":0.001726382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004060122,"about_ca_topic_score_gemma":0.004204431,"domain_scores_codex":[0.9980801,0.0007154863,0.0001229269,0.0003858857,0.0006004137,0.00009517009],"domain_scores_gemma":[0.9808225,0.01506727,0.000829485,0.001277659,0.001632865,0.0003703152],"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":[0.0007883848,0.0003066375,0.009143627,0.0003544764,0.0003107862,0.00007392641,0.0002900859,0.5213302,0.003762903,0.03273578,0.002100214,0.4288029],"study_design_scores_gemma":[0.00003501793,0.00007112028,0.0006451336,0.00002509493,0.00002082086,0.00004418971,0.00002344178,0.9880095,0.001599989,0.008978442,0.0005303762,0.00001681413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02806111,0.0008519277,0.9682406,0.0002671437,0.00007629362,0.00007144466,0.00005078772,0.0004688063,0.001911915],"genre_scores_gemma":[0.4526277,0.0005982309,0.5415729,0.0002866102,0.0001343039,0.0002345518,0.0003310948,0.0003559807,0.003858601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0053409,"threshold_uncertainty_score":0.02824575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1008153029018901,"score_gpt":0.3667202816540406,"score_spread":0.2659049787521505,"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."}}