{"id":"W4386431062","doi":"10.1007/978-3-031-43111-1_23","title":"Model-Based Policy Optimization with Neural Differential Equations for Robotic Arm Control","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Reinforcement learning; Robotic arm; Artificial intelligence; Trajectory; Process (computing); Artificial neural network; Task (project management); Node (physics); Robot; Sample (material); System dynamics; Machine learning; Engineering","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":[0.0006212288,0.0008847349,0.001532228,0.0003718084,0.0004066411,0.001055289,0.001176243,0.001725109,0.004027697],"category_scores_gemma":[0.001996515,0.0008553239,0.0007877132,0.0006748199,0.0009126841,0.0008395315,0.001417677,0.001850595,0.0007321984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123758,"about_ca_system_score_gemma":0.0008933115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009506062,"about_ca_topic_score_gemma":0.007377015,"domain_scores_codex":[0.9997643,0.0000844682,0.00001139288,0.00004053033,0.00007459114,0.00002465643],"domain_scores_gemma":[0.9995926,0.0002625275,0.00004368441,0.00001987509,0.00006518319,0.00001604972],"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":[0.00001363968,0.00001623081,0.00004254256,0.00004153797,0.00001788184,0.00001295217,0.00001326451,0.9753966,0.0003295531,0.01362074,0.0008026741,0.009692375],"study_design_scores_gemma":[0.00000240527,0.000003937731,0.00001297821,0.000003029428,0.000001645265,0.000002099679,0.00000110808,0.9955568,0.00004431199,0.00407883,0.0002909996,0.000001920531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003860119,0.001264632,0.9858304,0.0003141491,0.0001331847,0.00002613545,0.00004825574,0.0002144785,0.008308584],"genre_scores_gemma":[0.7845483,0.001745141,0.176484,0.0003012501,0.0002393023,0.0004347606,0.0002193839,0.0003291807,0.03569857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009506062,"threshold_uncertainty_score":0.01890141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02859191668905308,"score_gpt":0.2611185300663834,"score_spread":0.2325266133773303,"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."}}