{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002327298,0.0001803729,0.0002955048,0.00007973375,0.000375523,0.0001737847,0.001512429,0.00007041315,0.000005240654],"category_scores_gemma":[0.002208543,0.0001133936,0.00006906054,0.0007697128,0.0005769173,0.0001506027,0.0004718563,0.0002580807,0.000002951745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006066305,"about_ca_system_score_gemma":0.0000908607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003270555,"about_ca_topic_score_gemma":0.0002366487,"domain_scores_codex":[0.9979954,0.0003747098,0.0006335867,0.0004044402,0.0002353231,0.0003565166],"domain_scores_gemma":[0.9968705,0.001780294,0.0003762969,0.0007312485,0.0001980754,0.00004361862],"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":[0.00004864595,0.00004294043,0.007104582,0.00006798737,0.00003092308,6.8925e-7,0.01040407,0.6588489,0.005068832,0.06448582,0.00003421429,0.2538624],"study_design_scores_gemma":[0.00002821581,0.00008760605,0.001136529,0.0001379379,0.000007399344,0.000002642892,0.0001373099,0.949399,0.02662312,0.02214844,0.0001566957,0.0001350854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01684576,0.00005651842,0.9804161,0.0005722437,0.0008506401,0.0005190744,9.868444e-7,0.000049243,0.0006894831],"genre_scores_gemma":[0.7168425,0.000003516472,0.2828715,0.0001062759,0.0000766349,0.00002639166,4.915146e-7,0.000007020046,0.00006563711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6999968,"threshold_uncertainty_score":0.4624059,"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."}}