{"id":"W2753431380","doi":"","title":"Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kronecker delta; Reinforcement learning; Computer science; Scalability; Curvature; Trust region; Mathematical optimization; Artificial intelligence; 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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005815895,0.0002551364,0.0002616931,0.0002306056,0.001898817,0.004508691,0.0008807207,0.0001467531,0.00001409629],"category_scores_gemma":[0.0004203799,0.0002488572,0.00006641103,0.0001901072,0.00005134557,0.01330426,0.0001908517,0.0002159446,0.00001976368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001952874,"about_ca_system_score_gemma":0.0001315459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001919547,"about_ca_topic_score_gemma":7.354698e-7,"domain_scores_codex":[0.9978343,0.000051657,0.0009035399,0.0002489633,0.0005469827,0.0004145177],"domain_scores_gemma":[0.9965259,0.0000456303,0.001950781,0.0005884051,0.0007948318,0.00009449761],"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":[0.000008880264,0.000004031198,0.0001266751,0.0004079302,0.00001116529,1.959664e-7,0.00135836,0.9882395,0.00008445798,0.0009411682,0.00003644527,0.008781224],"study_design_scores_gemma":[0.0007152815,0.00008612093,0.00006322516,0.0001279247,0.00001275168,0.00001489496,0.0002211185,0.9958208,0.0003058278,0.00001029124,0.002331352,0.0002904263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001869432,0.00003146362,0.9936087,0.0001024438,0.0009695865,0.000911873,7.245289e-7,0.0002444733,0.002261294],"genre_scores_gemma":[0.9138038,0.000003218796,0.08535161,0.00009412473,0.0001234884,0.00008327051,0.0001047282,0.00001912872,0.0004166764],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9119343,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0371741992360738,"score_gpt":0.2844571715789954,"score_spread":0.2472829723429216,"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."}}