{"id":"W3101152497","doi":"","title":"On Efficiency in Hierarchical Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning","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":[0.0003362418,0.0001779818,0.0001990824,0.0002195242,0.0001983371,0.0007986889,0.0006401035,0.00007611387,0.000004831317],"category_scores_gemma":[0.000325969,0.0001595421,0.00003924947,0.0007874134,0.00002905866,0.00272128,0.00014487,0.0005297707,0.0002267251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009271195,"about_ca_system_score_gemma":0.000084589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009821619,"about_ca_topic_score_gemma":8.990173e-8,"domain_scores_codex":[0.9979104,0.0000875898,0.0007551874,0.0002059846,0.0006884954,0.0003523047],"domain_scores_gemma":[0.9991436,0.0000790734,0.0003502994,0.0001910034,0.0001001006,0.0001358991],"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":[0.000009961518,0.00000478628,0.0001721406,0.000153486,0.000001555781,0.000002716479,0.003575384,0.9793579,0.00002657,0.01060501,0.0001779235,0.005912583],"study_design_scores_gemma":[0.0004277038,0.0002970287,0.0001108222,0.0001100609,0.000001186209,0.000007322609,0.0001530774,0.9949936,0.00007002713,0.00001377331,0.003641473,0.0001739602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006040853,0.0000281533,0.9810825,0.001318716,0.0003083738,0.0003381538,1.374644e-7,0.0004015244,0.01048159],"genre_scores_gemma":[0.9976439,0.000002420623,0.0005362935,0.001607013,0.00005166674,0.0000238463,0.00001034291,0.000007135075,0.0001173403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9916031,"threshold_uncertainty_score":0.7701775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02283141343365988,"score_gpt":0.2504900927677116,"score_spread":0.2276586793340517,"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."}}