{"id":"W2739573821","doi":"10.3390/make1010002","title":"Learning to Teach Reinforcement Learning Agents","year":2017,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Washington State University; U.S. Department of Agriculture; National Aeronautics and Space Administration; National Science Foundation","keywords":"Reinforcement learning; Advice (programming); Heuristics; Statistic; Action (physics); Variance (accounting); Quality (philosophy); Discounting","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":[0.001765212,0.0008875584,0.0008937666,0.0003280568,0.0003086401,0.0006809475,0.001411718,0.001275343,0.002854305],"category_scores_gemma":[0.01442176,0.0003478916,0.0003441427,0.000332747,0.001150686,0.001316622,0.0008191156,0.001702194,0.00036415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063343,"about_ca_system_score_gemma":0.0011236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052906,"about_ca_topic_score_gemma":0.002562469,"domain_scores_codex":[0.9991597,0.0004317409,0.00003301474,0.0001479052,0.0001278654,0.00009974799],"domain_scores_gemma":[0.9943039,0.004350332,0.0004475229,0.0002938322,0.0003553197,0.0002489858],"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":[0.0001446207,0.0002238285,0.001762868,0.0001021635,0.00006490502,0.00009061272,0.0001630102,0.9158089,0.001006506,0.03067068,0.001032412,0.04892946],"study_design_scores_gemma":[0.00003507019,0.00005955312,0.0001184079,0.000007320721,0.000007102466,0.00001160825,0.00001154211,0.9851724,0.000260336,0.01388235,0.0004296736,0.000004646145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07430705,0.0002724693,0.91887,0.0009021224,0.00006875837,0.0001270432,0.00005040497,0.0004694462,0.00493261],"genre_scores_gemma":[0.9086771,0.000188487,0.08585128,0.0002304852,0.00005281666,0.0002704777,0.00006334483,0.00004147368,0.004624431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003052906,"threshold_uncertainty_score":0.009548664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352967150582671,"score_gpt":0.323069848083718,"score_spread":0.2995401765778913,"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."}}