{"id":"W3159382640","doi":"10.48550/arxiv.2104.12365","title":"Efficient Hyperparameter Optimization for Physics-based Character Animation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Motion and Animation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperparameter; Computer science; Bayesian optimization; Pruning; Machine learning; Artificial intelligence; Animation; Character (mathematics); Reinforcement learning; Character animation; Fidelity; Computer animation; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007317949,0.00019715,0.0001911123,0.0001088721,0.00007119322,0.00008946678,0.0001292323,0.0001799484,0.0001595279],"category_scores_gemma":[0.00001376325,0.0002544402,0.000170964,0.0001574731,0.00002001309,0.00008249346,0.00004643665,0.0001836421,0.00002639735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001889111,"about_ca_system_score_gemma":0.00003561923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002268353,"about_ca_topic_score_gemma":0.000002016745,"domain_scores_codex":[0.9992597,0.00003089397,0.0001468459,0.0003516412,0.00004955448,0.0001614001],"domain_scores_gemma":[0.9994123,0.00003401226,0.00008012108,0.0002713307,0.0001465478,0.00005571196],"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":[0.000009708187,0.00004591127,0.00003570623,0.0002228831,0.00003089571,0.000003341947,0.00007657516,0.9975994,0.0004272969,0.001252838,0.00004387573,0.0002516297],"study_design_scores_gemma":[0.0004071256,0.00001409436,0.0003336906,0.00009119567,0.00006523247,2.12078e-7,0.00002926764,0.9978589,0.0007095193,0.0001455827,0.00009111979,0.0002540181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3846147,0.00000785011,0.6143738,0.000009266472,0.0002480064,0.0002342209,0.00002155487,0.0001898817,0.000300736],"genre_scores_gemma":[0.9944243,0.00001260126,0.004642302,0.00004450361,0.0001144765,0.000004603042,0.0005756007,0.00003797387,0.0001435978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6098096,"threshold_uncertainty_score":0.9999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06140588456391558,"score_gpt":0.1747119115497372,"score_spread":0.1133060269858216,"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."}}