{"id":"W4364375123","doi":"10.1016/j.eswa.2023.120112","title":"Neural Network-based control using Actor-Critic Reinforcement Learning and Grey Wolf Optimizer with experimental servo system validation","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education and Research, Romania; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; Corporation for National and Community Service","keywords":"Reinforcement learning; Computer science; Artificial neural network; Particle swarm optimization; Gradient descent; Convergence (economics); Process (computing); Controller (irrigation); Mathematical optimization; Servomechanism; Artificial intelligence; Machine learning; Control engineering; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003427774,0.0002934615,0.0003468468,0.0001394927,0.0006241458,0.0004272615,0.0003769122,0.00007242877,0.000001432337],"category_scores_gemma":[0.000007679695,0.0002383075,0.00004181279,0.0006824944,0.00009127535,0.0004400292,0.00007007579,0.0001578546,0.00001421157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002686635,"about_ca_system_score_gemma":0.0001023299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001839903,"about_ca_topic_score_gemma":0.000003090484,"domain_scores_codex":[0.9978552,0.000175377,0.0003807634,0.0006155946,0.0004498485,0.0005232234],"domain_scores_gemma":[0.9986292,0.0001766943,0.0002647018,0.0005401484,0.0002071966,0.0001821285],"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":[0.00006188562,0.00003191,0.001466954,0.00006707534,0.00008602951,0.0000150758,0.0005114914,0.9852293,0.002166573,0.009899206,0.00004229003,0.0004221698],"study_design_scores_gemma":[0.00166389,0.0001911389,0.0000715889,0.000172636,0.00002248344,0.00006360534,0.0009324583,0.9954854,0.0001764272,0.000001897046,0.0009142016,0.0003042775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009770974,0.000473082,0.9861659,0.000169242,0.0001197617,0.002271989,0.000002288169,0.0009193888,0.0001073189],"genre_scores_gemma":[0.9801533,0.000001574053,0.01615902,0.00007048986,0.0001817531,0.00325486,0.00003318865,0.0000433539,0.0001025159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9703823,"threshold_uncertainty_score":0.9717899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01517488254014964,"score_gpt":0.2595307435211804,"score_spread":0.2443558609810307,"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."}}