{"id":"W4403741606","doi":"10.1177/02783649241285161","title":"Reinforcement learning for versatile, dynamic, and robust bipedal locomotion control","year":2024,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Simon Fraser University","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Robot; Robustness (evolution); Reinforcement learning; Computer science; Robot locomotion; Robotics; Artificial intelligence; Control engineering; Control theory (sociology); Robot control; Engineering; Control (management); Mobile robot","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001596652,0.0000838968,0.0001214088,0.0002962844,0.0000896543,0.0002918165,0.0003393481,0.00004428284,0.00005119745],"category_scores_gemma":[0.0001714193,0.00005951975,0.00008546362,0.0001056188,0.00006678591,0.0001638794,0.00004014636,0.0005493833,0.00001499239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002230012,"about_ca_system_score_gemma":0.0000670108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000422162,"about_ca_topic_score_gemma":0.000004713836,"domain_scores_codex":[0.9986359,0.00006833069,0.0003145732,0.00007785769,0.0007061174,0.0001971868],"domain_scores_gemma":[0.9986531,0.0006174881,0.0000397044,0.0000696931,0.0005514921,0.00006856613],"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":[0.00006232958,0.000009517018,0.00002439515,0.00003163328,0.0002775734,0.00001698391,0.000223737,0.9783557,0.001148016,0.004460902,0.001378651,0.01401053],"study_design_scores_gemma":[0.0008547124,0.0001416204,0.000112144,0.0001110664,0.00002475095,0.0000801684,0.0001821392,0.9934893,0.00009986791,0.001081519,0.003765551,0.00005722079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00294231,0.001158286,0.9853209,0.008331193,0.001325461,0.0002582128,0.000002363973,0.00003961598,0.0006216978],"genre_scores_gemma":[0.9970623,0.0005785082,0.001175373,0.00003513871,0.000366797,0.000008795349,0.000003641606,0.00002156886,0.0007478612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.99412,"threshold_uncertainty_score":0.2813993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03771074436780729,"score_gpt":0.3304997103891537,"score_spread":0.2927889660213464,"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."}}