{"id":"W4385756663","doi":"10.1109/lra.2023.3304561","title":"Torque-Based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer","year":2023,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Research Foundation of Korea","keywords":"Reinforcement learning; Torque; Robot; Task (project management); Computer science; Artificial intelligence; Action (physics); Control (management); Position (finance); Process (computing); Space (punctuation); Control theory (sociology); Control engineering; 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":[0.0006719743,0.0005225679,0.0004142431,0.0001671592,0.0002031848,0.00039571,0.000714669,0.0005316156,0.00225407],"category_scores_gemma":[0.001929384,0.0002168527,0.0002366585,0.0001582903,0.0007686503,0.0005795079,0.0008187465,0.0009905768,0.000448084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005347821,"about_ca_system_score_gemma":0.0004969593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001563741,"about_ca_topic_score_gemma":0.001610006,"domain_scores_codex":[0.9998355,0.00004881552,0.000009260569,0.00003553522,0.00004145188,0.00002938667],"domain_scores_gemma":[0.9995843,0.0001911924,0.00004751994,0.00007095769,0.000070412,0.00003562183],"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":[0.0001334796,0.0001012645,0.0006551945,0.00009747247,0.00002982482,0.00009999564,0.00008408889,0.8679807,0.00921175,0.01388229,0.001510434,0.1062134],"study_design_scores_gemma":[0.000004219641,0.00003677133,0.00005135846,0.000004370109,0.000001919126,0.00001014251,0.00000346721,0.995684,0.0010712,0.002775007,0.0003549704,0.000002494158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03620429,0.0002689452,0.9584794,0.0002501307,0.00007800366,0.00003655658,0.00002624005,0.00117768,0.003478646],"genre_scores_gemma":[0.9294308,0.0001201056,0.0678251,0.0001634994,0.00002641614,0.00005527266,0.00005183233,0.00007792852,0.002249038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00225407,"threshold_uncertainty_score":0.007540584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01552998923633645,"score_gpt":0.2354284983620097,"score_spread":0.2198985091256732,"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."}}