{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001327919,0.0006279405,0.0008046945,0.0003241459,0.0002874446,0.0005900014,0.001094863,0.0007387594,0.002086141],"category_scores_gemma":[0.004983312,0.0004100009,0.0004331802,0.000248629,0.0008376793,0.0006854495,0.0008241663,0.001406742,0.0003335152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001098332,"about_ca_system_score_gemma":0.001213044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008602907,"about_ca_topic_score_gemma":0.005923197,"domain_scores_codex":[0.9996953,0.0001370026,0.0000184346,0.00004538549,0.00006811752,0.00003565175],"domain_scores_gemma":[0.9981341,0.001326426,0.0001116534,0.0001111852,0.0002458977,0.00007081751],"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":[0.00001466863,0.000007638917,0.0001168022,0.00001689201,0.000006132291,0.000006451462,0.00001081387,0.9923728,0.0002333372,0.001940586,0.00008606225,0.005187817],"study_design_scores_gemma":[0.000002152848,0.000003441255,0.000008461454,0.000001308638,5.165124e-7,6.405648e-7,7.481723e-7,0.9992301,0.00006434425,0.0006332583,0.00005436196,6.016838e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0182651,0.0002020934,0.9793471,0.0002057622,0.00003194415,0.00003760396,0.00002439573,0.0005311808,0.001354918],"genre_scores_gemma":[0.8079786,0.0001825225,0.1896495,0.0001133024,0.00002409202,0.0002457227,0.00008398489,0.0001314727,0.001590908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008602907,"threshold_uncertainty_score":0.0171057,"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."}}