{"id":"W4391421221","doi":"10.48550/arxiv.2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Civil, Mechanical and Manufacturing Innovation; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Reinforcement learning; Reinforcement; Computer science; Bipedalism; Control (management); Artificial intelligence; Engineering; Biology; Structural engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001528631,0.0003044223,0.0003229866,0.0002201537,0.00009686527,0.00009115057,0.0001801165,0.0002659403,0.00006247919],"category_scores_gemma":[0.00001748704,0.0003595302,0.0001779209,0.000124764,0.00004882779,0.00008033781,0.0001837515,0.0006022779,0.00005170574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002818149,"about_ca_system_score_gemma":0.00003960793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002236664,"about_ca_topic_score_gemma":0.00002388854,"domain_scores_codex":[0.998934,0.00003665869,0.000202623,0.0004762999,0.00005787239,0.0002925857],"domain_scores_gemma":[0.999413,0.00007536752,0.00006680906,0.0002537048,0.00006708916,0.0001241048],"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":[0.0000381294,0.00001000138,0.00009219999,0.0004228943,0.0002437134,0.00002418902,0.00009648308,0.9904565,0.00005175229,0.00723897,0.0001923509,0.001132855],"study_design_scores_gemma":[0.001553431,0.00006089566,0.0001367833,0.000130212,0.0002942258,0.000002158627,0.0001171116,0.9934151,0.00001219082,0.00335599,0.0005835565,0.0003384108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03768126,0.0002526075,0.9576006,0.0001045514,0.0008690188,0.0008587021,0.00001671058,0.0005808946,0.00203565],"genre_scores_gemma":[0.9965468,0.0002644885,0.0001877389,0.0000255374,0.00008246826,0.00000849128,0.00006159692,0.00005218769,0.002770667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9588656,"threshold_uncertainty_score":0.9998857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278355826780596,"score_gpt":0.1650210791604898,"score_spread":0.1371854964824302,"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."}}