{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004161545,0.0001820926,0.0001547414,0.0001479796,0.0008902648,0.000129924,0.0005589948,0.00002707451,0.0005181428],"category_scores_gemma":[0.00004976392,0.0002034358,0.00009835872,0.0003121536,0.00002755813,0.0004552505,0.0004193509,0.0001770925,0.000005134755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003833011,"about_ca_system_score_gemma":0.0001537182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008776398,"about_ca_topic_score_gemma":1.777739e-7,"domain_scores_codex":[0.9982954,0.0001346829,0.0002748856,0.0005211869,0.0003866947,0.000387202],"domain_scores_gemma":[0.9992034,0.0001889914,0.0001307796,0.0002857511,0.00008749723,0.0001036034],"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":[0.00004131772,0.00005828765,0.000003064036,0.000002428785,0.00001138551,0.000004861066,0.0004152554,0.9919907,0.003121256,0.002661433,0.00007216794,0.00161783],"study_design_scores_gemma":[0.001242425,0.0004779953,0.000001254041,0.000002435425,0.000003497972,0.0000090064,0.0004186699,0.9521381,0.04314327,0.00005221869,0.002259182,0.0002519495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003850076,0.00002192565,0.9979005,0.0001470346,0.0003808425,0.0007470201,0.000001653664,0.0003476019,0.0004149165],"genre_scores_gemma":[0.2260112,4.325941e-7,0.772183,0.0003191946,0.00003950479,0.0004674692,0.0000265501,0.00002235453,0.000930239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2259727,"threshold_uncertainty_score":0.829587,"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."}}