{"id":"W2109909644","doi":"","title":"Cost-Sensitive Exploration in Bayesian Reinforcement Learning","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; ENCODE; Artificial intelligence; Total cost; Bayesian probability; Machine learning; Partially observable Markov decision process; Mathematical optimization; Bayesian optimization; Markov process; Markov chain; Markov model; Mathematics; Economics","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":[0.002631081,0.001010318,0.001425913,0.0004970107,0.0003988618,0.001019212,0.001397529,0.001439149,0.00203825],"category_scores_gemma":[0.01216429,0.00066808,0.0005152114,0.0005451215,0.001853522,0.002232307,0.001558046,0.001800633,0.0001847842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00179438,"about_ca_system_score_gemma":0.001266545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004075246,"about_ca_topic_score_gemma":0.003121913,"domain_scores_codex":[0.9983088,0.0009564611,0.00005591486,0.0001921697,0.0003427916,0.0001439617],"domain_scores_gemma":[0.9948526,0.0039652,0.0004127554,0.0002128191,0.0003331161,0.0002235005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005572214,0.00003036586,0.0004309032,0.00006193625,0.00002867725,0.00004920666,0.00005669261,0.9321111,0.0004893808,0.05808942,0.0003247996,0.008271839],"study_design_scores_gemma":[0.00001569763,0.00002167629,0.0000589751,0.000007036991,0.00000429594,0.000008274555,0.000004195752,0.9678159,0.0001009458,0.03179125,0.000166285,0.000005594563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04701057,0.0005815958,0.9475405,0.000590614,0.00003894026,0.00005081113,0.00006423404,0.000175674,0.003947006],"genre_scores_gemma":[0.917487,0.0003455323,0.07889765,0.0001610156,0.00004358105,0.0002127045,0.00007882168,0.00007554125,0.002698208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004075246,"threshold_uncertainty_score":0.01391464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04822342128543226,"score_gpt":0.2852717858225678,"score_spread":0.2370483645371356,"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."}}