{"id":"W4200199148","doi":"10.1017/s0263574721001600","title":"A model-free deep reinforcement learning approach for control of exoskeleton gait patterns","year":2021,"lang":"en","type":"article","venue":"Robotica","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Exoskeleton; Gait; Reinforcement learning; Artificial intelligence; Computer science; Robotics; Rehabilitation robotics; Gait training; Simulation; Engineering; Rehabilitation; Robot; Physical medicine and rehabilitation; Medicine; Physical therapy","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":[0.0007479204,0.0005835635,0.0005832515,0.0002085462,0.0002063135,0.0004240527,0.0009739506,0.000656441,0.001552642],"category_scores_gemma":[0.001496263,0.0003815406,0.000334614,0.0001394171,0.0005532467,0.0004333753,0.0008092202,0.0009046558,0.0002307759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005951705,"about_ca_system_score_gemma":0.0007593076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005588176,"about_ca_topic_score_gemma":0.004771575,"domain_scores_codex":[0.9997725,0.00006060965,0.00001352189,0.00006037716,0.00005726429,0.00003588145],"domain_scores_gemma":[0.9994963,0.0002152668,0.00008933019,0.00004980003,0.0001135228,0.00003566887],"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":[0.00004859217,0.00005134779,0.0002291936,0.0000342625,0.0000202819,0.00003832814,0.00002976845,0.9565397,0.003356911,0.002156449,0.0004793895,0.03701589],"study_design_scores_gemma":[0.000002528575,0.00001013231,0.00001689141,9.959986e-7,9.837061e-7,0.000002337502,5.52688e-7,0.9995415,0.000155558,0.0002163682,0.00005112392,0.00000103789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01832103,0.00009853439,0.9794905,0.0001347291,0.00002853193,0.00002840612,0.00002078807,0.0005278073,0.001349741],"genre_scores_gemma":[0.9341504,0.00005345824,0.06293583,0.0001228624,0.00002158177,0.00009355677,0.0000421142,0.00004695554,0.002533199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005588176,"threshold_uncertainty_score":0.01111132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01222400624733375,"score_gpt":0.2152118795009143,"score_spread":0.2029878732535806,"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."}}