{"id":"W4319441257","doi":"10.1016/j.neucom.2023.01.076","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning☆","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Successor cardinal; Generalization; Artificial intelligence; Feature (linguistics); Machine learning; Sample (material); Knowledge transfer; Kalman filter; Stability (learning theory); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007413689,0.000465281,0.0004018147,0.0002578533,0.001096285,0.000649188,0.001551762,0.0001331903,0.000008334448],"category_scores_gemma":[0.0001170543,0.0004811558,0.0002290504,0.001344878,0.00008160585,0.0004743696,0.0006524678,0.001023478,0.00008396427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578083,"about_ca_system_score_gemma":0.0002041185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003539693,"about_ca_topic_score_gemma":0.000001927894,"domain_scores_codex":[0.9960269,0.0001784071,0.0005712557,0.0009462894,0.0009456531,0.001331513],"domain_scores_gemma":[0.9982836,0.0002961095,0.0001935884,0.0007995336,0.0002064096,0.0002208077],"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":[0.00001145872,0.00001102467,0.0005013772,0.00007965499,0.00001699433,0.00008836229,0.0006815255,0.9934852,0.001369731,0.0002375489,0.0003466036,0.003170484],"study_design_scores_gemma":[0.0007950467,0.0001290077,0.0001313059,0.0001122552,0.00001310978,0.00002057668,0.00004747629,0.9942748,0.001871228,0.00002729632,0.002095798,0.0004821296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1102133,0.000009225647,0.8865426,0.0005598895,0.0005259141,0.0004074825,0.000002534338,0.001493852,0.0002451772],"genre_scores_gemma":[0.9886619,0.00000471349,0.009270641,0.0009376768,0.0001650946,0.00001351679,0.00005092601,0.00007230417,0.0008232685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8784486,"threshold_uncertainty_score":0.999764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03375625906198634,"score_gpt":0.2968388084657638,"score_spread":0.2630825494037775,"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."}}