{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006420344,0.00009105053,0.0001094189,0.0000271017,0.00006956203,0.00002949905,0.00005460625,0.00003174437,0.0005326361],"category_scores_gemma":[0.00001050369,0.00006798557,0.00003086441,0.00004544311,0.00002338923,0.00005860044,0.000003798855,0.00005465616,0.0001439575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003197611,"about_ca_system_score_gemma":0.000007366252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005540527,"about_ca_topic_score_gemma":0.00003189586,"domain_scores_codex":[0.9995168,0.000005824489,0.000113363,0.00008387294,0.00007696929,0.0002031079],"domain_scores_gemma":[0.9997358,0.000030926,0.00001486233,0.00009700422,0.00006149078,0.00005992857],"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":[0.0000721132,0.000008587747,0.0002840906,0.00002568878,0.0001257137,0.00000143134,0.0001971144,0.9795467,0.0008050997,0.004843543,0.001989789,0.01210017],"study_design_scores_gemma":[0.002614966,0.0002721639,0.0002201767,0.000008539354,0.0000212337,0.000003969207,0.00009011583,0.9814153,0.0007449174,0.00003014102,0.01445193,0.0001265151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001173756,0.00001575003,0.9495835,0.0001516312,0.0001223414,0.0002894947,1.571055e-7,0.0002688112,0.04839458],"genre_scores_gemma":[0.9932042,0.000001957296,0.00218872,0.0002316052,0.000172115,0.00005821467,0.00000257956,0.00002074653,0.0041198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9920305,"threshold_uncertainty_score":0.5831992,"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."}}