{"id":"W2460299708","doi":"10.1145/2897824.2925881","title":"Terrain-adaptive locomotion skills using deep reinforcement learning","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Human Motion and Animation","field":"Engineering","cited_by":203,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Terrain; LEAPS; Computer science; Artificial intelligence; Morphing; Parameterized complexity; Workbench; Human–computer interaction; Visualization; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001030085,0.0001390672,0.00009791392,0.0002561766,0.0002087074,0.00002356423,0.0001010418,0.00008726411,0.0003428588],"category_scores_gemma":[0.00001437409,0.0001179256,0.00009114846,0.0002192298,0.00003918675,0.0002357538,0.000002025326,0.0001927322,0.0000816833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001067128,"about_ca_system_score_gemma":0.000006963875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000447402,"about_ca_topic_score_gemma":0.00002318136,"domain_scores_codex":[0.9992713,0.00003278059,0.000198985,0.0001387136,0.0001699189,0.000188248],"domain_scores_gemma":[0.9995892,0.00005833633,0.00003266048,0.0002102021,0.00004475333,0.00006484487],"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":[0.00001667071,0.0000964996,0.0001146702,0.00003468159,0.0001172142,0.000002697943,0.001259858,0.8774998,0.01569633,0.002073161,0.0000458075,0.1030426],"study_design_scores_gemma":[0.003034858,0.0007092363,0.005421497,0.0007304279,0.0001753858,0.00003362382,0.0007000462,0.9408535,0.03278024,0.007737136,0.006480571,0.001343425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04980396,0.00001008387,0.9489279,0.0001148662,0.0001961094,0.0001217737,0.000001797628,0.0003311413,0.0004923943],"genre_scores_gemma":[0.9975222,0.0001319866,0.002008738,0.00006146649,0.00003640054,0.00001318052,0.000003685463,0.00002982037,0.0001925422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9477182,"threshold_uncertainty_score":0.4808865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01886496579044436,"score_gpt":0.2354751051931255,"score_spread":0.2166101394026811,"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."}}