{"id":"W3132089310","doi":"10.1109/iros45743.2020.9341019","title":"Learning Domain Randomization Distributions for Training Robust Locomotion Policies","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Context (archaeology); Machine learning; Task (project management); Generalization; Extrapolation; Domain (mathematical analysis); Interpolation (computer graphics); Range (aeronautics); Mathematics; Statistics; Engineering","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":[0.002775985,0.001024099,0.001062065,0.0008157603,0.0003794746,0.0006320665,0.001330238,0.001320889,0.001607481],"category_scores_gemma":[0.01363777,0.0007816073,0.0005434365,0.0003852371,0.001433128,0.001578079,0.001573548,0.002126405,0.000557623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018391,"about_ca_system_score_gemma":0.001110169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001645934,"about_ca_topic_score_gemma":0.001670763,"domain_scores_codex":[0.9990006,0.000488021,0.0000527726,0.000219461,0.0001491702,0.00008998437],"domain_scores_gemma":[0.9932269,0.005200333,0.0005364672,0.0004448537,0.0003736971,0.0002177254],"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":[0.0001067574,0.00006945739,0.0006484482,0.00003582292,0.00002010118,0.00002389651,0.00003661233,0.974346,0.001175171,0.004003966,0.0002913729,0.01924232],"study_design_scores_gemma":[0.00001307392,0.00004018745,0.00005657905,0.000006415733,0.000002378151,0.000005770974,0.000004397776,0.9964142,0.0004786796,0.002858626,0.0001157429,0.000003902793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05450063,0.000263107,0.9427246,0.0001985894,0.0000267484,0.00009808207,0.00005290777,0.0009539689,0.001181292],"genre_scores_gemma":[0.8195722,0.000211771,0.1778031,0.0002234281,0.00003683171,0.0004179436,0.000256772,0.000183432,0.00129452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002775985,"threshold_uncertainty_score":0.01468098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05326927639304079,"score_gpt":0.25799983112925,"score_spread":0.2047305547362092,"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."}}