{"id":"W4390035554","doi":"10.1101/2023.12.19.572447","title":"Reinforcement Learning for Control of Human Locomotion in Simulation","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Toronto Rehabilitation Institute; AGE-WELL","keywords":"Reinforcement learning; Computer science; Exoskeleton; Artificial intelligence; Imitation; Action (physics); Robot; Simulation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005435441,0.0002394,0.0003711122,0.0003240978,0.00005446365,0.00003797689,0.000157435,0.0002980581,0.00000513161],"category_scores_gemma":[0.0001702295,0.0002814081,0.0001104672,0.0002208421,0.00003628048,0.00005367834,0.00006064219,0.0003557886,0.000006978129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002022019,"about_ca_system_score_gemma":0.00005300542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000926604,"about_ca_topic_score_gemma":0.000001613477,"domain_scores_codex":[0.9986216,0.0000409563,0.0006105113,0.0002833941,0.0001855154,0.0002579747],"domain_scores_gemma":[0.9989809,0.0001426419,0.000193584,0.0003540715,0.0002692081,0.00005954208],"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":[0.000006202507,0.00002093237,0.002195602,0.0008321046,0.00003959373,8.116624e-7,0.00001835499,0.8917192,0.104608,0.0005487625,0.000009213482,0.000001264988],"study_design_scores_gemma":[0.0008039878,0.00008293359,0.02715651,0.0003997367,0.0000370311,3.084159e-10,0.000003027615,0.9536303,0.01738242,0.00001795941,0.0001817882,0.0003043392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4411354,0.0001762626,0.5555845,0.00006482624,0.0008349342,0.001638702,0.00003765306,0.0005234889,0.000004276797],"genre_scores_gemma":[0.998135,0.00003577862,0.001424377,0.000006807714,0.00008983491,0.0002004933,0.000001113777,0.0001023989,0.000004228295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5569996,"threshold_uncertainty_score":0.9999638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01727358426663469,"score_gpt":0.2411089147021429,"score_spread":0.2238353304355082,"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."}}