{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005557345,0.0001217297,0.0001162791,0.0001648454,0.00008903704,0.0001029297,0.0002528453,0.00005189593,0.00004865273],"category_scores_gemma":[0.0001010312,0.0001168985,0.00003111718,0.0003571601,0.00001834032,0.002086877,0.0001872438,0.0002225278,0.000289873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001281924,"about_ca_system_score_gemma":0.00002724995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003333877,"about_ca_topic_score_gemma":0.000004958541,"domain_scores_codex":[0.9987021,0.00009898369,0.0002707069,0.0001785866,0.0003046632,0.0004449571],"domain_scores_gemma":[0.999391,0.00008314806,0.00009557248,0.0002718939,0.00005053561,0.0001078601],"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":[0.000002716354,0.00001192562,0.004769788,0.000003654618,0.000004573115,0.00000258432,0.003548576,0.9380254,0.0001139847,0.04802112,0.0001230716,0.005372609],"study_design_scores_gemma":[0.0002759224,0.00006972748,0.002467881,0.00001682525,0.000001888434,0.000004019049,0.0004874076,0.9900811,0.002349969,0.00006431014,0.00399806,0.0001829176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000544893,0.000008537426,0.9610342,0.0003755208,0.0002629622,0.0002455518,1.567527e-8,0.0001672257,0.03736111],"genre_scores_gemma":[0.9691322,0.00001271262,0.02728001,0.0003154893,0.00006317903,0.00002227266,0.000005966637,0.000008358189,0.003159785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9685873,"threshold_uncertainty_score":0.4766981,"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."}}