{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008251238,0.0006448692,0.001077645,0.0002966368,0.0004209802,0.0007118738,0.001419817,0.000800909,0.002306527],"category_scores_gemma":[0.00247436,0.0004203832,0.0005000152,0.0002550135,0.0006415854,0.0009624157,0.001668714,0.001150251,0.0003824499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006532755,"about_ca_system_score_gemma":0.00103888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004463919,"about_ca_topic_score_gemma":0.003804731,"domain_scores_codex":[0.9996177,0.00007783232,0.00001996347,0.00009852598,0.0001116539,0.00007424418],"domain_scores_gemma":[0.9989982,0.0004634448,0.0001205911,0.0001547721,0.0001789845,0.00008395144],"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":[0.0002460041,0.0001960127,0.0006026312,0.00006443077,0.00005514679,0.0001000712,0.00009557998,0.8740503,0.008094897,0.005488746,0.001091953,0.1099143],"study_design_scores_gemma":[0.000006058778,0.00002689478,0.00005698432,0.000001897466,0.000003207599,0.000007242133,0.000002510193,0.9980872,0.0004695476,0.001257952,0.000077257,0.000003056827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07660862,0.000188016,0.917935,0.000191093,0.00007819522,0.00007868814,0.0000405711,0.00105659,0.003823195],"genre_scores_gemma":[0.9687448,0.00003358329,0.02969898,0.00003920776,0.00001248951,0.00006242553,0.00003213525,0.0000374101,0.001339021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004463919,"threshold_uncertainty_score":0.008875847,"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."}}