{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003489279,0.0005288715,0.0005106002,0.001210607,0.0003969033,0.0007664287,0.002305229,0.0002460432,0.000005992594],"category_scores_gemma":[0.0002546618,0.0004612158,0.00014542,0.0007874994,0.0004483598,0.000473662,0.0003677889,0.0005281125,0.00001090774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003433249,"about_ca_system_score_gemma":0.001214238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001079268,"about_ca_topic_score_gemma":0.00002129664,"domain_scores_codex":[0.9964967,0.0000305108,0.0005162386,0.001186056,0.001017698,0.0007527974],"domain_scores_gemma":[0.9968965,0.001016552,0.0003954096,0.001102804,0.0004206031,0.0001681288],"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":[0.00001331298,0.00001554799,0.000005057595,0.00003325493,0.00001365009,0.000005930549,0.0001131925,0.9644946,0.00001143976,0.02533691,0.00000399325,0.009953125],"study_design_scores_gemma":[0.0009060277,0.0004092178,0.000007710353,0.0001696045,0.0000264785,0.000004485726,4.93909e-8,0.9896081,0.00003596694,0.008316916,0.000006502275,0.0005089422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001197107,0.0000132361,0.9960095,0.001501114,0.0008872649,0.001017492,0.000005835001,0.0003445813,0.0002197385],"genre_scores_gemma":[0.3545599,0.000003365841,0.6427855,0.001234411,0.0004245342,0.00005506488,0.00003980728,0.00007598224,0.0008214723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3545587,"threshold_uncertainty_score":0.9997839,"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."}}