{"id":"W4403675482","doi":"10.1109/biorob60516.2024.10719807","title":"Reinforcement Learning for Control of Human Locomotion in Simulation","year":2024,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Control (management); Artificial intelligence; Human–computer interaction; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004239025,0.00005304591,0.0001078275,0.0001667607,0.0000299424,0.00007044135,0.0001035292,0.0000300055,0.0000233077],"category_scores_gemma":[0.00003719185,0.00005067818,0.00004859021,0.0001795441,0.000006799703,0.0004294885,0.00002418589,0.00005512382,0.00001369173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005087294,"about_ca_system_score_gemma":0.00002063081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005286437,"about_ca_topic_score_gemma":0.00003094297,"domain_scores_codex":[0.9993352,0.00004711965,0.0002447666,0.0001602259,0.000121054,0.00009160455],"domain_scores_gemma":[0.9994448,0.0003102824,0.00005149996,0.0001054817,0.00007137971,0.00001659415],"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":[0.00001542699,0.0000600739,0.001671668,0.0002820524,0.00004228484,0.000002987082,0.001728131,0.6473638,0.01272886,0.05862162,0.0001152255,0.2773679],"study_design_scores_gemma":[0.0004252725,0.0001180462,0.0003827407,0.00007879474,0.000002443749,6.382497e-7,0.00002469804,0.9954831,0.001432403,0.0007741728,0.001221871,0.0000557947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009962479,0.00002424882,0.9878872,0.0001745936,0.0001358275,0.0004002147,3.033074e-7,0.0001156092,0.0012995],"genre_scores_gemma":[0.9989567,3.978392e-7,0.0003411341,0.00002382622,0.00002869218,0.00003900731,0.000003599579,0.000004109109,0.0006025253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9889942,"threshold_uncertainty_score":0.2066596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03932292210613274,"score_gpt":0.3183529776514953,"score_spread":0.2790300555453625,"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."}}