{"id":"W4388820294","doi":"10.1109/tie.2023.3331074","title":"Model-Based Reinforcement Learning With Probabilistic Ensemble Terminal Critics for Data-Efficient Control Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea","keywords":"Reinforcement learning; Probabilistic logic; Computer science; Trajectory; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00137514,0.0008923073,0.00103703,0.0003865595,0.0003092716,0.0007883424,0.001302239,0.0008175588,0.001391722],"category_scores_gemma":[0.004221848,0.0004540295,0.000482957,0.000349927,0.0008121709,0.000802384,0.001073225,0.001920133,0.0003111416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007451483,"about_ca_system_score_gemma":0.001197584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004604191,"about_ca_topic_score_gemma":0.003674057,"domain_scores_codex":[0.9995137,0.0001254161,0.00003009573,0.00009318445,0.0001784805,0.00005900865],"domain_scores_gemma":[0.9985915,0.0007565471,0.0001783396,0.0001217978,0.0002904097,0.00006138439],"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":[0.0000412037,0.00002055082,0.0003499947,0.00002818579,0.00001956085,0.00002768956,0.000024189,0.9746302,0.0009101942,0.003074178,0.0003347581,0.02053928],"study_design_scores_gemma":[0.000002717919,0.000009476983,0.00002172402,0.000001993295,0.000001957272,0.000003695492,8.647712e-7,0.9989908,0.0001898999,0.0006871416,0.00008799682,0.000001690448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01210528,0.0002128895,0.9859214,0.0001073582,0.00002781704,0.00002203278,0.00002191039,0.0004562995,0.001124989],"genre_scores_gemma":[0.8995781,0.0001595873,0.09834104,0.0001056573,0.00003406379,0.0001100889,0.00009613088,0.00007769577,0.00149758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004604191,"threshold_uncertainty_score":0.009154797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06410995923129628,"score_gpt":0.2901327633149109,"score_spread":0.2260228040836146,"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."}}