{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000701298,0.0006175108,0.0004845659,0.0002138084,0.0002207987,0.0004388075,0.0007566571,0.0004937389,0.001230682],"category_scores_gemma":[0.001890218,0.000250823,0.0003039328,0.0001538055,0.0006805465,0.0004326301,0.000652181,0.001106446,0.0002164619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000643866,"about_ca_system_score_gemma":0.0006018695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003071151,"about_ca_topic_score_gemma":0.002587784,"domain_scores_codex":[0.999806,0.00004872329,0.00001222718,0.0000499966,0.00005292648,0.00003011955],"domain_scores_gemma":[0.9995153,0.0002467151,0.00006580479,0.00004739592,0.00009143638,0.00003340866],"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":[0.00003585444,0.00003820258,0.000412246,0.00005512052,0.00002853461,0.00004489483,0.00002955796,0.9494926,0.004094968,0.006269738,0.000621844,0.03887646],"study_design_scores_gemma":[0.000004027007,0.00002068904,0.00004788375,0.000003346134,0.000002244944,0.00000461859,0.000001741556,0.9975466,0.0003718795,0.001773989,0.0002206797,0.000002250225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02466123,0.0005008877,0.9714332,0.0002006286,0.00005009721,0.00003582861,0.00002794687,0.000661374,0.002428899],"genre_scores_gemma":[0.9365738,0.0002391262,0.06083696,0.0001235308,0.00003237057,0.00009192105,0.00006164294,0.00005015288,0.001990431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003071151,"threshold_uncertainty_score":0.006106555,"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."}}