{"id":"W3112128648","doi":"10.1109/smc42975.2020.9283306","title":"End-to-End Deep Reinforcement Learning for Exoskeleton Control","year":2020,"lang":"en","type":"article","venue":"","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Exoskeleton; Reinforcement learning; Computer science; Gait; Robot; Personalization; Synchronization (alternating current); Artificial intelligence; Gait training; Human–computer interaction; Simulation; Rehabilitation; Physical medicine and rehabilitation","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":[0.0005857825,0.0005607118,0.0004811057,0.0001144849,0.00018515,0.0002811535,0.0007604195,0.0006324892,0.001614442],"category_scores_gemma":[0.001257621,0.0002416458,0.0001880144,0.00009171614,0.0004392287,0.0003837358,0.0006484381,0.0009172484,0.0002340488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003939281,"about_ca_system_score_gemma":0.0005744228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002845488,"about_ca_topic_score_gemma":0.003266013,"domain_scores_codex":[0.9998418,0.00003911181,0.000009817262,0.00003648491,0.00004194701,0.00003080985],"domain_scores_gemma":[0.9997086,0.0001322128,0.00003645988,0.00003458057,0.00006069798,0.00002743627],"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":[0.0001533567,0.0001529285,0.0004892773,0.00005917994,0.00002918421,0.00008866542,0.00004542792,0.8874277,0.009779809,0.001980989,0.001010532,0.09878307],"study_design_scores_gemma":[0.000004203567,0.00002673065,0.00004705902,0.000001899096,0.000001386189,0.000005895933,0.000001363717,0.9985121,0.0008573604,0.0004424392,0.00009772128,0.000001733932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03867426,0.0001759669,0.9582295,0.0001299953,0.00004171639,0.00004074918,0.00002530456,0.001152362,0.001530152],"genre_scores_gemma":[0.9439125,0.00005913249,0.05385205,0.00007120221,0.000009766986,0.00007015323,0.00004031575,0.00003331899,0.001951481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002845488,"threshold_uncertainty_score":0.005657792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009691935156591523,"score_gpt":0.2158209086904908,"score_spread":0.2061289735338993,"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."}}