{"id":"W4285186326","doi":"10.1109/lra.2022.3187262","title":"Sample-Efficient Policy Adaptation for Exoskeletons Under Variations in the Users and the Environment","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Exoskeleton; Computer science; Robot; Sample (material); Controller (irrigation); Adaptation (eye); Set (abstract data type); Traverse; Simulation; Artificial intelligence","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":[0.0003792115,0.00008117889,0.00007918498,0.00009297726,0.0003145553,0.00005754123,0.0000754349,0.00001824782,0.000002377237],"category_scores_gemma":[0.00002621976,0.00005791778,0.00003131275,0.00013175,0.00007834915,0.00003058493,0.00001723451,0.00009613272,5.316213e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007738831,"about_ca_system_score_gemma":0.00001198899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003497678,"about_ca_topic_score_gemma":0.000004841267,"domain_scores_codex":[0.9993656,0.00007903807,0.0001851886,0.00009787115,0.0001474843,0.0001248117],"domain_scores_gemma":[0.9992543,0.0005616033,0.00003964501,0.0001175486,0.000007316329,0.00001954421],"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":[0.000002044378,0.00001444247,0.00002644507,0.00001162316,0.000009027111,7.970066e-8,0.002881658,0.8961704,0.0001765071,0.100118,0.00009797494,0.0004917806],"study_design_scores_gemma":[0.0006296866,0.00001765416,0.003806897,0.000002948402,0.00001731521,0.000002147214,0.0009094998,0.991194,0.000004171071,0.002756923,0.0005827298,0.00007602242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06498757,0.00005884694,0.8935416,0.0406333,0.0001489041,0.0005564617,0.00002941298,0.00003231016,0.00001162036],"genre_scores_gemma":[0.9892314,0.00002990351,0.009119751,0.001371088,0.00002936785,0.0001819157,0.00001949936,0.00001263255,0.000004462356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9242438,"threshold_uncertainty_score":0.2419337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01150709115248886,"score_gpt":0.2134674201461765,"score_spread":0.2019603289936876,"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."}}