{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001994553,0.0001033624,0.0001188844,0.0001073538,0.0002293201,0.0003139515,0.0001725842,0.00004105633,0.00001208663],"category_scores_gemma":[0.0008421664,0.0001038033,0.00004356788,0.0002617598,0.00001819625,0.0004835437,0.0002208024,0.0001576787,0.000008107192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000089452,"about_ca_system_score_gemma":0.0001242731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004629641,"about_ca_topic_score_gemma":0.000008272917,"domain_scores_codex":[0.9990882,0.00005750308,0.0001844675,0.000298687,0.0001388711,0.000232304],"domain_scores_gemma":[0.9987265,0.0007225855,0.00009624572,0.0001725244,0.0002235655,0.00005856201],"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":[0.000005960718,0.000006013066,0.0007631931,0.00003028667,0.00002434385,0.000002264828,0.002062897,0.9098073,0.001021254,0.05471846,0.00003943251,0.03151864],"study_design_scores_gemma":[0.000306792,0.0000692175,0.000823593,0.00004635977,0.000005344093,0.00001203392,0.00104395,0.9892213,0.001407868,0.001152806,0.005763009,0.0001477393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003007285,0.00002893744,0.9922154,0.00154035,0.0001487034,0.0001158849,3.568953e-7,0.0001119524,0.002831127],"genre_scores_gemma":[0.7595336,0.000020466,0.2369088,0.0004996445,0.0001032738,0.00001305707,0.00001737476,0.00001159522,0.00289225],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7565263,"threshold_uncertainty_score":0.4232976,"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."}}