{"id":"W2964114602","doi":"10.1109/iros.2018.8593722","title":"Feedback Control For Cassie With Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":189,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Robot; Markov decision process; Feedback linearization; Motion control; Linearization; Control theory (sociology); Robust control; Artificial intelligence; Control engineering; Terrain; Control system; Markov process; Control (management); Engineering; Nonlinear system; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004960636,0.0005351612,0.0005758601,0.0001899634,0.0003038679,0.0004707537,0.0005721652,0.0006080397,0.00216674],"category_scores_gemma":[0.001245921,0.0002686667,0.0003005622,0.0001410546,0.0008395575,0.0003085801,0.0009182758,0.0009516648,0.0001994148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009153316,"about_ca_system_score_gemma":0.0009271031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01159909,"about_ca_topic_score_gemma":0.01083486,"domain_scores_codex":[0.9998746,0.0000219853,0.000005974313,0.00003285803,0.00003665145,0.00002798389],"domain_scores_gemma":[0.9996158,0.0001981923,0.00005276463,0.00003116714,0.0000707261,0.00003119839],"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":[0.00004257724,0.00001911145,0.0002464441,0.00003248101,0.0000120415,0.00003428346,0.00002564128,0.9821699,0.001320011,0.005233807,0.0004670008,0.0103968],"study_design_scores_gemma":[0.000004094604,0.00001220182,0.00002281675,0.000001832943,0.000001464402,0.00000208288,0.000001669413,0.9985318,0.0001647458,0.001120763,0.0001353221,0.000001237604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07065988,0.0004353248,0.917515,0.0005368466,0.00009840006,0.0000620192,0.00009150854,0.001388649,0.009212377],"genre_scores_gemma":[0.9708057,0.00006641604,0.02626469,0.0000912043,0.00001269449,0.0000746542,0.0000570657,0.00003839916,0.002589141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01159909,"threshold_uncertainty_score":0.02306318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006971797119189254,"score_gpt":0.1992258258131533,"score_spread":0.1922540286939641,"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."}}