{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006959062,0.0003005892,0.0002920014,0.0003008907,0.0007370525,0.000224692,0.00114448,0.0001944689,0.000005890893],"category_scores_gemma":[0.00008640592,0.0002903224,0.00009640712,0.000984404,0.00008987563,0.0002189711,0.000009444285,0.0008694906,0.00003825974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003695061,"about_ca_system_score_gemma":0.001309889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006412998,"about_ca_topic_score_gemma":0.000008097918,"domain_scores_codex":[0.997257,0.00008175996,0.000500521,0.0007024992,0.0006121417,0.0008460675],"domain_scores_gemma":[0.9975443,0.0006005974,0.0001929683,0.001187436,0.0003190723,0.0001555768],"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":[0.0001353882,0.00008741302,0.000001354398,0.00002704953,0.00005428175,0.000001724933,0.00004977972,0.9873679,0.00009751274,0.00292895,0.0002166768,0.009032027],"study_design_scores_gemma":[0.00266358,0.001185624,2.351949e-7,0.00003921394,0.0001275657,0.000003967035,0.00001419415,0.9877784,0.001271725,0.0001098363,0.006481495,0.000324204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001884801,0.000007846822,0.9962108,0.0004541579,0.0002866193,0.002086681,0.0000238295,0.000583067,0.0001585802],"genre_scores_gemma":[0.986236,0.00001059321,0.01128578,0.0001730634,0.0001351181,0.001129727,0.00009946088,0.00005168637,0.0008785806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9860475,"threshold_uncertainty_score":0.9999549,"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."}}