{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006961669,0.0006261243,0.000489437,0.0002151393,0.0002194232,0.0004459212,0.0007589285,0.0005000841,0.001262808],"category_scores_gemma":[0.001913209,0.00025261,0.0003083657,0.0001539097,0.0006779358,0.0004309308,0.000656068,0.001118797,0.0002235472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006355755,"about_ca_system_score_gemma":0.0006044625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003049952,"about_ca_topic_score_gemma":0.002586875,"domain_scores_codex":[0.9998041,0.00004865169,0.00001234485,0.0000508273,0.0000535475,0.00003056753],"domain_scores_gemma":[0.9995091,0.0002500211,0.00006631903,0.00004795499,0.00009254107,0.00003401618],"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":[0.0000363595,0.00003866394,0.0004165356,0.00005683588,0.00002901564,0.00004647099,0.00002995706,0.9496189,0.004167228,0.006317324,0.0006392062,0.03860349],"study_design_scores_gemma":[0.000004055057,0.00002083575,0.00004832838,0.000003457108,0.000002275607,0.000004711401,0.000001753271,0.9975395,0.0003701192,0.001780201,0.0002225296,0.000002287534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02454566,0.0005101608,0.9714636,0.0002026701,0.00005178263,0.00003621608,0.0000289221,0.0006719822,0.002488924],"genre_scores_gemma":[0.9372149,0.0002414057,0.0601556,0.0001268937,0.00003287333,0.00009312967,0.00006408974,0.00005145072,0.002019666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003049952,"threshold_uncertainty_score":0.006064355,"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."}}