{"id":"W88806592","doi":"10.1007/978-3-642-28499-1_5","title":"Leveraging Domain Knowledge to Learn Normative Behavior: A Bayesian Approach","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; University of Waterloo","funders":"","keywords":"Normative; Computer science; Reinforcement learning; Norm (philosophy); Domain knowledge; Artificial intelligence; Set (abstract data type); Domain (mathematical analysis); Adaptation (eye); Process (computing); Normative model of decision-making; Bayesian probability; Machine learning; Knowledge management; Psychology; Epistemology; 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":[0.005042315,0.001378257,0.002060826,0.001787608,0.0005678391,0.002301909,0.00316405,0.00216221,0.003342435],"category_scores_gemma":[0.02072806,0.00128773,0.001479352,0.001281174,0.002407233,0.005554229,0.002326818,0.004565438,0.0006022935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001347692,"about_ca_system_score_gemma":0.001577479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003001489,"about_ca_topic_score_gemma":0.004942756,"domain_scores_codex":[0.9976951,0.001018495,0.0001348314,0.0005129218,0.0004966326,0.0001419285],"domain_scores_gemma":[0.9871842,0.01002595,0.0007695771,0.0009689829,0.0007758978,0.0002754462],"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":[0.0001682962,0.0003569509,0.002831228,0.0002976923,0.0003783076,0.0001224147,0.0003392748,0.572278,0.001994633,0.2372099,0.003188115,0.1808353],"study_design_scores_gemma":[0.00001291541,0.00002952962,0.0002624015,0.00003494397,0.00002643393,0.00002312534,0.00001745333,0.7740043,0.0003824613,0.2247178,0.0004685504,0.0000201466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008152233,0.0002194654,0.9882368,0.0004777746,0.00002158362,0.00003812681,0.00007113808,0.0001709434,0.002611838],"genre_scores_gemma":[0.5957327,0.001035236,0.3969839,0.0004421923,0.0002064226,0.0004325044,0.0004242798,0.0001920204,0.004550749],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005042315,"threshold_uncertainty_score":0.02666664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530434686639648,"score_gpt":0.2616365253215557,"score_spread":0.2363321784551592,"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."}}