{"id":"W1496855202","doi":"10.48550/arxiv.1301.6690","title":"Model-Based Bayesian Exploration","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Value of information; Action (physics); Bayesian probability; Quality (philosophy); Artificial intelligence; Value (mathematics); Machine learning; Probability distribution; Mathematical optimization; Mathematics; Statistics","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":[0.002133285,0.0009622574,0.001577065,0.001022639,0.0005901604,0.001980171,0.001754894,0.001385522,0.004955596],"category_scores_gemma":[0.009571326,0.000744114,0.0008366693,0.000993052,0.001546713,0.003038081,0.00191524,0.002010569,0.0007883726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887278,"about_ca_system_score_gemma":0.001774324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415092,"about_ca_topic_score_gemma":0.005593801,"domain_scores_codex":[0.9987634,0.0005842911,0.00004997272,0.0002199469,0.0002925618,0.00008981128],"domain_scores_gemma":[0.9970394,0.002021674,0.0002726184,0.0002514258,0.000298393,0.0001164205],"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":[0.00007831826,0.00004702756,0.0008798898,0.0001220454,0.00006733849,0.00006175652,0.0001008111,0.7935006,0.0004632267,0.160047,0.001812631,0.0428193],"study_design_scores_gemma":[0.00001874118,0.00001885458,0.0001182562,0.00002500906,0.00001133218,0.00002312073,0.00001172844,0.8400288,0.0001955015,0.1579914,0.001546332,0.00001107573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01034926,0.0006014179,0.9806249,0.0007207014,0.00003170467,0.00003963692,0.0001076728,0.0002636145,0.007261127],"genre_scores_gemma":[0.777607,0.001333282,0.2122416,0.0003662325,0.0001177299,0.000316571,0.0003546103,0.0001441359,0.007518826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004955596,"threshold_uncertainty_score":0.01657808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07631130262408777,"score_gpt":0.1767027802933835,"score_spread":0.1003914776692957,"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."}}