{"id":"W4413945504","doi":"10.1109/icra55743.2025.11128275","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","year":2025,"lang":"en","type":"article","venue":"","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Value (mathematics); Imitation; Control (management); Artificial intelligence; Machine learning; Psychology","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":[0.001788774,0.0009377662,0.0009616159,0.0003902404,0.0003783291,0.0009400384,0.001853498,0.001093485,0.003652572],"category_scores_gemma":[0.009707917,0.0006590026,0.0005005947,0.0003058719,0.001815653,0.001740574,0.002762903,0.002253639,0.0006063747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006498657,"about_ca_system_score_gemma":0.00116426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00134911,"about_ca_topic_score_gemma":0.001725717,"domain_scores_codex":[0.9989644,0.0003937142,0.00004991438,0.0002000858,0.0002840085,0.0001078526],"domain_scores_gemma":[0.9949813,0.0033721,0.0004016418,0.0006430694,0.0003582347,0.0002436703],"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":[0.0002612731,0.0001018566,0.0006413806,0.0001370942,0.00003123004,0.0001450494,0.0001582691,0.8743094,0.006700344,0.041856,0.001917418,0.07374061],"study_design_scores_gemma":[0.00001949707,0.00004781479,0.00004759869,0.000009967755,0.000003380241,0.00002204105,0.000005691443,0.9862557,0.001128695,0.01205177,0.0004023967,0.000005338805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02469566,0.00009999955,0.9712259,0.0001979925,0.00002066688,0.00005376944,0.0000337003,0.0008230376,0.002849295],"genre_scores_gemma":[0.7780885,0.0001138307,0.2170753,0.0001535825,0.00002778803,0.0002700743,0.0001390549,0.0002641362,0.003867711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003652572,"threshold_uncertainty_score":0.01221907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01817088014745695,"score_gpt":0.2582764828963096,"score_spread":0.2401056027488526,"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."}}