{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00162316,0.0008216865,0.0007222875,0.00145715,0.0004851678,0.0008722865,0.005090105,0.0003900243,0.00003477708],"category_scores_gemma":[0.00007974366,0.0007912568,0.0001881476,0.00110918,0.0005245422,0.001064939,0.003305217,0.001548961,0.0003443021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008017113,"about_ca_system_score_gemma":0.0005332526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001569077,"about_ca_topic_score_gemma":0.0000098807,"domain_scores_codex":[0.9947803,0.00009929289,0.0007508522,0.001681518,0.001329797,0.001358211],"domain_scores_gemma":[0.9965062,0.0003510524,0.0003781414,0.001962799,0.000295837,0.0005060205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005664852,0.00006138084,0.0001527968,0.00006205193,0.00001715722,0.00003500262,0.01195441,0.4555805,0.000062913,0.01664466,0.00004915824,0.5153742],"study_design_scores_gemma":[0.000452939,0.0004158519,0.0003946288,0.0005130742,0.00002862457,0.0001898682,0.000003191329,0.9714596,0.0003592238,0.01175505,0.01246005,0.001967913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003324723,0.0003536838,0.973544,0.0003041892,0.00167376,0.0009028536,0.000001720951,0.0002856995,0.02290081],"genre_scores_gemma":[0.1343446,0.00001368454,0.8624771,0.001019395,0.0006069849,0.00004674334,0.000008863148,0.00007254445,0.001410121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.515879,"threshold_uncertainty_score":0.9994538,"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."}}