{"id":"W4387323309","doi":"10.1145/3618375","title":"AdaptNet: Policy Adaptation for Physics-Based Character Control","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; École de Technologie Supérieure; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Reinforcement learning; Adaptation (eye); Computer science; Scratch; Embedding; Task (project management); Hierarchy; Code (set theory); Space (punctuation); Character (mathematics); Control (management); Human–computer interaction; Artificial intelligence; Programming language; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006676081,0.0008764104,0.0005887348,0.0003802191,0.0003075545,0.0006427556,0.001600429,0.0008802078,0.005285928],"category_scores_gemma":[0.002371519,0.0005244436,0.000495045,0.0002224276,0.0007319671,0.0008902369,0.001275233,0.001719099,0.001065873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007473839,"about_ca_system_score_gemma":0.0009829107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005200142,"about_ca_topic_score_gemma":0.007156355,"domain_scores_codex":[0.9997372,0.00004970844,0.00001362249,0.00008554645,0.00007671524,0.00003722987],"domain_scores_gemma":[0.9995856,0.0001847564,0.000036363,0.00008073795,0.00007197601,0.00004062455],"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":[0.0001530317,0.0001346618,0.0009309649,0.00009800813,0.00006112801,0.0001077091,0.00006996468,0.8358765,0.007082786,0.01020832,0.006052537,0.1392244],"study_design_scores_gemma":[0.000007306722,0.00001886168,0.00005684891,0.000004155676,0.00000304208,0.000009867683,0.000003103879,0.9954345,0.001020845,0.002313138,0.001124344,0.000003986425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01311032,0.0002322089,0.9731345,0.0001737745,0.0002093645,0.00010835,0.0001618298,0.008573025,0.004296625],"genre_scores_gemma":[0.7033135,0.0003272903,0.2835288,0.0004263759,0.0001286745,0.0005542195,0.0006237655,0.001097393,0.01000006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005285928,"threshold_uncertainty_score":0.01768315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0520802048763096,"score_gpt":0.2875373411699848,"score_spread":0.2354571362936752,"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."}}