{"id":"W7132871321","doi":"","title":"Who Should I Trust? Uncertainty and Risk for Knowledge Transfer from Multiple Sources in Reinforcement Learning Domains","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Knowledge transfer; Transfer of learning; Set (abstract data type); Inference; Quality (philosophy); Bayesian inference; Uncertainty quantification; Bayesian probability","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":[0.01620542,0.001080705,0.001712286,0.001130447,0.001212639,0.004430302,0.00228106,0.003655271,0.002931563],"category_scores_gemma":[0.08060551,0.001050434,0.001260826,0.0007970618,0.006405393,0.009707193,0.005359698,0.006366752,0.0003425133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003259302,"about_ca_system_score_gemma":0.001598644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002715666,"about_ca_topic_score_gemma":0.001276409,"domain_scores_codex":[0.9890692,0.006350528,0.0005066006,0.001743745,0.001676428,0.0006535025],"domain_scores_gemma":[0.9214678,0.06734466,0.004912779,0.003174258,0.001835297,0.001265072],"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":[0.0003763443,0.0001446915,0.004251983,0.000258607,0.0002096839,0.0005735308,0.001390489,0.4674405,0.001012489,0.4671047,0.001292282,0.05594476],"study_design_scores_gemma":[0.00002919408,0.00005858469,0.0005774013,0.00005549688,0.00002602449,0.00009547609,0.00009988476,0.4735937,0.0005346221,0.5241827,0.0007112829,0.00003551512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06284183,0.0007128947,0.9251029,0.004723003,0.00004867803,0.00008729759,0.00009997194,0.0001980134,0.006185311],"genre_scores_gemma":[0.9527125,0.0003920115,0.04440477,0.0003978127,0.00008660444,0.0001511162,0.00006108556,0.00006942224,0.00172463],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01620542,"threshold_uncertainty_score":0.08570355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04253784223620904,"score_gpt":0.326914110571627,"score_spread":0.284376268335418,"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."}}