{"id":"W2546975091","doi":"","title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Robustness (evolution); Reinforcement learning; Computer science; Artificial intelligence; Torque; Machine learning; Physics","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":[0.0002058805,0.0001138647,0.0001098189,0.0001103493,0.0001994221,0.00004310698,0.0006333923,0.00005820075,0.00004804742],"category_scores_gemma":[0.00006886493,0.00007147124,0.00007039392,0.0004488234,0.00008175283,0.0007657071,0.0002513836,0.0001358636,0.00009794847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001228309,"about_ca_system_score_gemma":0.00002883932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007299505,"about_ca_topic_score_gemma":0.000008932317,"domain_scores_codex":[0.9990956,0.0001581884,0.0001263896,0.0003054352,0.00009632999,0.000218039],"domain_scores_gemma":[0.9988663,0.0002641436,0.0002515489,0.0004738814,0.00009579642,0.0000482896],"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":[0.000004739676,0.00001720041,0.07973522,0.00001153494,0.0000214779,0.000004917559,0.0001627577,0.9007028,0.005967107,0.01245455,0.00002312648,0.0008945575],"study_design_scores_gemma":[0.0005974778,0.0001003209,0.02865972,0.0001199359,0.00004064628,0.000006304685,0.0001680054,0.9583537,0.009538287,0.001165529,0.0009965253,0.0002535307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3904491,0.000001495332,0.6087761,0.000150642,0.0001470549,0.00006355339,1.274281e-7,0.00005137323,0.0003606065],"genre_scores_gemma":[0.9956481,0.00002157475,0.001307254,0.00003193603,0.00003658871,1.139925e-7,2.478749e-7,0.00000859726,0.002945553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6074688,"threshold_uncertainty_score":0.2914513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0546902574138028,"score_gpt":0.2072281283393214,"score_spread":0.1525378709255186,"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."}}