{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002896329,0.0005717278,0.0006677789,0.0002237724,0.0001878891,0.0009252681,0.0008189018,0.000900765,0.001420317],"category_scores_gemma":[0.01221998,0.0003374146,0.00028179,0.0001958328,0.0008901008,0.00209661,0.0008007227,0.001603078,0.0003769353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006137429,"about_ca_system_score_gemma":0.000838961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00327244,"about_ca_topic_score_gemma":0.003699179,"domain_scores_codex":[0.9993584,0.000257648,0.00003954429,0.0001443521,0.00008830818,0.0001117848],"domain_scores_gemma":[0.9964727,0.002413504,0.0003656518,0.0003021022,0.0002439387,0.0002021251],"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":[0.0006727288,0.000507521,0.01611348,0.0003110647,0.0001851109,0.00009551365,0.0001170737,0.6787559,0.01238352,0.0048199,0.001519769,0.2845185],"study_design_scores_gemma":[0.00003318812,0.0001423411,0.0012928,0.00002612312,0.00001584337,0.00001697974,0.00002452547,0.9909552,0.002408646,0.004893962,0.0001824456,0.000007975934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6608105,0.001592258,0.3297504,0.001917161,0.00009655191,0.0001008373,0.0001672639,0.001113748,0.004451344],"genre_scores_gemma":[0.980911,0.0001960268,0.0179809,0.0001258082,0.000009532539,0.00002640274,0.00009147699,0.0000380144,0.0006207738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00327244,"threshold_uncertainty_score":0.01531738,"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."}}