{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001979826,0.0003096648,0.0005845032,0.0001852075,0.00006830939,0.0000488716,0.0002955589,0.0003069602,0.0001338072],"category_scores_gemma":[0.0000560743,0.0003820551,0.0003967383,0.0001880645,0.00004974242,0.0001204481,0.0001235429,0.0004361402,0.000008459211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001865335,"about_ca_system_score_gemma":0.00006840283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003907419,"about_ca_topic_score_gemma":0.00001155618,"domain_scores_codex":[0.9987095,0.00009411555,0.0003616807,0.0004408702,0.0000812343,0.0003125855],"domain_scores_gemma":[0.99892,0.0001216748,0.0002058089,0.0004335991,0.0002041563,0.0001148216],"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":[0.00008060296,0.00003834454,0.0002060041,0.0003378581,0.0003363568,0.00001904738,0.00008609228,0.9963534,0.0007505491,0.00119979,0.00003218053,0.0005597681],"study_design_scores_gemma":[0.002968431,0.00008018268,0.00016889,0.0001511134,0.0002558418,0.000001459335,0.0001508496,0.9951475,0.0003766336,0.0002803762,0.00008479853,0.0003338832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07359065,0.00008296296,0.9242724,0.00002108653,0.0005557712,0.0007228368,0.000007075785,0.0002248029,0.0005224244],"genre_scores_gemma":[0.9971807,0.0001561513,0.001601893,0.00001995182,0.00007204706,0.000009508663,0.0001132405,0.00004393174,0.0008025979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.92359,"threshold_uncertainty_score":0.9998631,"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."}}