{"id":"W4312930523","doi":"10.1115/detc2022-87995","title":"Reinforcement Learning Based Sequential Batch-Sampling for Bayesian Optimal Experimental Design","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Leverage (statistics); Bayesian optimization; Artificial intelligence; Suite; Bayesian probability; Machine learning; Time budget; Task (project management)","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":[0.01593464,0.002172489,0.004083537,0.001363952,0.0005790703,0.001375449,0.003434764,0.002446903,0.005156002],"category_scores_gemma":[0.0362187,0.001877164,0.001407903,0.0009215438,0.003012938,0.001644841,0.002351506,0.003582443,0.0005973681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003078998,"about_ca_system_score_gemma":0.004592229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005958012,"about_ca_topic_score_gemma":0.005746954,"domain_scores_codex":[0.9934094,0.004151754,0.0002768625,0.00109776,0.0006744285,0.0003898722],"domain_scores_gemma":[0.9501204,0.04255804,0.002646223,0.001521837,0.001974415,0.00117919],"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":[0.0006925956,0.0002066001,0.001134489,0.0003377642,0.0001303592,0.00009642052,0.00009020921,0.9287629,0.0009265037,0.027433,0.0007976769,0.03939152],"study_design_scores_gemma":[0.00008557383,0.00007582867,0.00008969985,0.00001629849,0.0000144375,0.000007261465,0.000003859213,0.987866,0.000307882,0.01131008,0.0002147789,0.000008228334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01198458,0.0004372569,0.9849561,0.0003117998,0.00006943956,0.0004907582,0.00009495418,0.0006049944,0.001050037],"genre_scores_gemma":[0.6060628,0.0003352439,0.3874291,0.0005513085,0.0001245176,0.002236033,0.0004079654,0.0001661101,0.00268702],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01593464,"threshold_uncertainty_score":0.08427137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04887043370431594,"score_gpt":0.3111594791720255,"score_spread":0.2622890454677095,"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."}}