{"id":"W3103898737","doi":"10.1109/tro.2022.3192969","title":"Joint Estimation of Expertise and Reward Preferences From Human Demonstrations","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Robotics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Robot; Leverage (statistics); Computer science; Human–robot interaction; Artificial intelligence; Set (abstract data type); Function (biology); Machine learning; Human–computer interaction; Human behavior; Space (punctuation)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001276525,0.000122236,0.000159313,0.0001571028,0.0005374268,0.00007015467,0.0003172787,0.000039136,0.0000659345],"category_scores_gemma":[0.0000065842,0.0001329131,0.00005543521,0.0002593292,0.00007340992,0.0002594326,0.00001084876,0.0002619204,0.000004999941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006781,"about_ca_system_score_gemma":0.00005815905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009893607,"about_ca_topic_score_gemma":0.00001604527,"domain_scores_codex":[0.9987566,0.0001010957,0.000363992,0.0002548546,0.0003759832,0.0001475017],"domain_scores_gemma":[0.999245,0.00009760474,0.0001533173,0.0003988094,0.00004263171,0.00006264387],"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":[0.000003024379,0.00007377893,0.00002661027,0.000006467481,0.00002356599,0.000001264729,0.0009618808,0.9875,0.0009994423,0.001867569,0.00003061185,0.008505857],"study_design_scores_gemma":[0.0002510488,0.0003120199,0.0003822339,0.00002226103,0.00002957172,0.000004143617,0.0001543843,0.9906264,0.006865567,0.001191481,0.00001258651,0.0001482959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01350957,0.00002253254,0.9852003,0.000321084,0.0004362165,0.0001695156,0.00001211619,0.0001101445,0.0002185564],"genre_scores_gemma":[0.8724741,0.00001504978,0.1272571,0.00005384907,0.000008379052,0.00003031961,0.000005806759,0.000008297644,0.0001470981],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8589645,"threshold_uncertainty_score":0.5420039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03686872366786004,"score_gpt":0.2569113578331829,"score_spread":0.2200426341653229,"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."}}