{"id":"W3148290239","doi":"10.48550/arxiv.2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Civil, Mechanical and Manufacturing Innovation; Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Robot locomotion; Robot; Computer science; Robust control; Set (abstract data type); Artificial intelligence; Bipedalism; Control engineering; Control (management); Parameterized complexity; Control theory (sociology); Control system; Engineering; Robot control; Mobile robot","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":[0.0008243179,0.0004999883,0.000593118,0.0002176152,0.0002397404,0.000413053,0.0006388933,0.000478947,0.001336146],"category_scores_gemma":[0.002803126,0.0002757764,0.0003254476,0.0001454047,0.0009930984,0.0004284322,0.0007215232,0.0008857222,0.0002175689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007944764,"about_ca_system_score_gemma":0.0007300037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003543487,"about_ca_topic_score_gemma":0.002197142,"domain_scores_codex":[0.9997641,0.00008369807,0.00001094427,0.00004761478,0.00006665067,0.00002690797],"domain_scores_gemma":[0.9992575,0.0004178073,0.0001138698,0.00007242639,0.00009691528,0.00004144641],"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":[0.00001741309,0.00001224859,0.0001292895,0.00002049741,0.00001065386,0.00001653716,0.00001366674,0.9855802,0.001298422,0.004854659,0.0001998124,0.007846485],"study_design_scores_gemma":[0.000003953799,0.00001058678,0.00002122322,0.000001807554,9.309281e-7,0.000002070433,0.000001027686,0.997658,0.0001607106,0.002037335,0.0001009288,0.000001458561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02337071,0.0002008047,0.9740442,0.0001710751,0.00002336199,0.00002692084,0.00002384609,0.0004198154,0.001719309],"genre_scores_gemma":[0.9426848,0.0001340679,0.05509612,0.00007225829,0.00001998207,0.0001032799,0.00006101976,0.00007529568,0.001753229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003543487,"threshold_uncertainty_score":0.007045746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05247399649437703,"score_gpt":0.1721798857875674,"score_spread":0.1197058892931904,"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."}}