{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007955314,0.0001103527,0.00008587811,0.0001238392,0.0001268953,0.0001180858,0.0006973111,0.00005624745,0.00005628883],"category_scores_gemma":[0.00001787389,0.0001238894,0.00005378835,0.0004509061,0.0000401428,0.001623452,0.0001225139,0.000106848,0.000526075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007370902,"about_ca_system_score_gemma":0.00006411895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002645691,"about_ca_topic_score_gemma":0.000003004254,"domain_scores_codex":[0.9992237,0.00004311014,0.00009923644,0.0003365224,0.0000725649,0.0002248799],"domain_scores_gemma":[0.9991118,0.00003861427,0.00007684858,0.000562534,0.0001027311,0.0001074643],"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":[0.000001426245,0.00001136145,0.0005378191,0.000003535274,0.000004370388,0.000007356103,0.00005994866,0.8980603,0.00007524983,0.1006505,0.0003345115,0.0002536747],"study_design_scores_gemma":[0.0002475162,0.00004017923,0.0001588941,0.000006533234,0.000005108656,3.237427e-7,0.00002290058,0.992088,0.000187328,0.006970929,0.0001245454,0.0001477634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01103663,0.000001714414,0.9833527,0.0002670486,0.00009162931,0.0001465984,1.595947e-7,0.0002309186,0.004872598],"genre_scores_gemma":[0.9812556,0.000003924738,0.01582843,0.0002552535,0.00001426493,8.150006e-7,0.000002776367,0.000007546967,0.002631409],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.970219,"threshold_uncertainty_score":0.6761805,"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."}}