{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002111644,0.0002436257,0.0002527547,0.0002859209,0.0002679053,0.0001335551,0.00006970058,0.00008838576,0.000008362636],"category_scores_gemma":[0.00004983954,0.0002563811,0.00007534433,0.0002387212,0.00002769794,0.0001102413,0.000009608204,0.0002040747,0.00002473939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009102841,"about_ca_system_score_gemma":0.0000144788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001569969,"about_ca_topic_score_gemma":0.000005871518,"domain_scores_codex":[0.9987483,0.0000477789,0.0003337884,0.0002560771,0.0002218436,0.0003922184],"domain_scores_gemma":[0.9994093,0.0002603605,0.00003713146,0.0001078011,0.00003659448,0.0001488713],"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":[0.00001331379,0.000006462372,0.0001752384,0.0001048069,0.00003741393,0.000004511676,0.0003053889,0.9596726,0.03653217,0.0001882822,0.0000945537,0.00286528],"study_design_scores_gemma":[0.001099447,0.0001286335,0.001244837,0.000105517,0.0000554336,0.000002125559,0.00004334647,0.9961789,0.0007108176,0.000009814987,0.0001282255,0.0002929604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1401895,0.00001032088,0.8565979,0.001734794,0.0003891898,0.0004507918,0.000001206189,0.0005880857,0.00003828536],"genre_scores_gemma":[0.995748,0.00002668894,0.003119005,0.0007491584,0.0001412447,0.00005015296,0.00004500894,0.00006090114,0.00005977804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8555586,"threshold_uncertainty_score":0.9999889,"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."}}