{"id":"W4313578038","doi":"10.1016/j.renene.2023.01.003","title":"Multi-objective deep reinforcement learning for optimal design of wind turbine blade","year":2023,"lang":"en","type":"article","venue":"Renewable Energy","topic":"Wind Energy Research and Development","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Mathematical optimization; Computer science; Pareto principle; Artificial intelligence; Stochastic optimization; Multi-objective optimization; Computation; Artificial neural network; Turbine; Turbine blade; Mathematics; Algorithm; Engineering","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":[0.000243593,0.0001730238,0.0002294242,0.0002429063,0.00009097678,0.00002028886,0.0001517226,0.00009084451,0.00005652102],"category_scores_gemma":[0.0000874297,0.000170179,0.00007111838,0.000440074,0.00002615539,0.00009111555,0.00006302247,0.00007885801,0.00001189913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110892,"about_ca_system_score_gemma":0.00007430302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000512162,"about_ca_topic_score_gemma":0.00005090033,"domain_scores_codex":[0.9987314,0.0000304494,0.000262528,0.0001967543,0.0002373312,0.0005415712],"domain_scores_gemma":[0.9994555,0.0001444528,0.00003597354,0.0001530594,0.00008018393,0.0001308448],"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":[0.00004925065,0.00001169793,0.00001933202,0.00004846428,0.0001208547,0.000006387472,0.000189357,0.9615275,0.03500998,0.00003747947,0.00163625,0.001343477],"study_design_scores_gemma":[0.0006659239,0.0001304559,0.0001021929,0.00002753836,0.000006929693,0.000001503933,0.00013322,0.8209773,0.1695537,0.00004030542,0.008194109,0.0001667741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005200449,0.0002649782,0.9920427,0.0000132443,0.0001683148,0.000142512,0.000001469555,0.0003162017,0.001850134],"genre_scores_gemma":[0.9596193,0.0005366512,0.02422655,0.00001448761,0.0001371807,0.0001635764,0.0001176775,0.00007619801,0.01510837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9678161,"threshold_uncertainty_score":0.6939697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02230934178238551,"score_gpt":0.2389649918070692,"score_spread":0.2166556500246837,"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."}}