{"id":"W4385430644","doi":"10.15607/rss.2023.xix.052","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Simon Fraser University","funders":"Division of Civil, Mechanical and Manufacturing Innovation; National Science Foundation","keywords":"Reinforcement learning; Computer science; Jumping; Artificial intelligence; Control engineering; Engineering; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00009457158,0.00008945511,0.0001141647,0.00004718424,0.00007335821,0.00003899759,0.00004243599,0.00003772881,0.0003102706],"category_scores_gemma":[0.00001810265,0.00008324337,0.00002894593,0.0001273132,0.00001350525,0.0001184475,0.00001608998,0.0001032154,0.000246355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002278415,"about_ca_system_score_gemma":0.000004895291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002131839,"about_ca_topic_score_gemma":0.000004034429,"domain_scores_codex":[0.9994532,0.00001185448,0.0001331113,0.00009860421,0.00009770478,0.0002055404],"domain_scores_gemma":[0.9998053,0.00004808257,0.00001171317,0.00007794427,0.00001284574,0.00004406898],"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":[0.000002846462,0.000001328158,0.0002653079,0.00001730098,0.00003238063,0.000003172808,0.0002754114,0.9931371,0.0004712793,0.001552014,0.001946476,0.002295358],"study_design_scores_gemma":[0.001071693,0.0000232432,0.000665686,0.00001105346,0.00001112403,0.000001778427,0.000366566,0.9888678,0.0001303001,0.00004540613,0.008696247,0.0001090575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02225328,0.0001212379,0.8903641,0.0007532349,0.0004801001,0.0003318311,8.015956e-7,0.002228548,0.08346687],"genre_scores_gemma":[0.9965458,0.00007908031,0.0003035365,0.0001667624,0.00006185083,0.00001678805,0.000005270257,0.00001678788,0.00280415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9742925,"threshold_uncertainty_score":0.3397246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02083073979581316,"score_gpt":0.209433677745489,"score_spread":0.1886029379496758,"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."}}