{"id":"W3181841583","doi":"10.1109/crv52889.2021.00018","title":"Uncertainty-Aware Policy Sampling and Mixing for Safe Interactive Imitation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Université de Montréal","funders":"","keywords":"Computer science; Trajectory; Process (computing); Imitation; Interactivity; Harm; Robot; Benchmark (surveying); Mixing (physics); Interleaving; Sampling (signal processing); Function (biology); Artificial intelligence; Human–computer interaction; Machine learning; Multimedia; Computer vision; Programming language","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":[0.003165953,0.001045764,0.001194771,0.0005950624,0.0006518256,0.001003051,0.001679261,0.001521253,0.001969432],"category_scores_gemma":[0.0172877,0.0007207202,0.0007832331,0.0003361356,0.002288406,0.00195308,0.003343947,0.002744877,0.0003668958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073797,"about_ca_system_score_gemma":0.001569993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001924847,"about_ca_topic_score_gemma":0.00168592,"domain_scores_codex":[0.9977664,0.0009099518,0.0001289982,0.0003650686,0.0006435262,0.000186078],"domain_scores_gemma":[0.9915081,0.00644048,0.0006248275,0.0006917971,0.0003735273,0.0003613128],"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":[0.0004578934,0.0001890814,0.001736783,0.0001218854,0.00006503343,0.0001804573,0.0004561035,0.8710424,0.006280159,0.04140934,0.0005525077,0.07750838],"study_design_scores_gemma":[0.00001994073,0.00006259557,0.00008610867,0.000008784959,0.000005887445,0.00002183445,0.00001137729,0.9858146,0.00173748,0.01193253,0.0002900931,0.000008744411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01438883,0.00008031219,0.9842009,0.000124182,0.00001376704,0.00005471104,0.00001383948,0.0003659341,0.0007576013],"genre_scores_gemma":[0.8345017,0.00009916701,0.163194,0.0001336041,0.0000425986,0.0002682222,0.0000675702,0.000118038,0.001575051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003165953,"threshold_uncertainty_score":0.01674342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03195446967103175,"score_gpt":0.31911333008798,"score_spread":0.2871588604169482,"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."}}