{"id":"W2803623613","doi":"10.1109/tnnls.2018.2832025","title":"Optimal Synchronization Control of Multiagent Systems With Input Saturation via Off-Policy Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Australian Research Council; Higher Education Discipline Innovation Project; Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Hamilton–Jacobi–Bellman equation; Reinforcement learning; Optimal control; Computer science; Synchronization (alternating current); Controller (irrigation); Control theory (sociology); Mathematical optimization; Artificial neural network; Bellman equation; Control (management); Mathematics; Artificial intelligence","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":[0.0004820779,0.0002737084,0.0003771543,0.0002230279,0.000612219,0.0002646735,0.0002378137,0.0001322665,0.000001841429],"category_scores_gemma":[0.00001690338,0.0002286927,0.00006568386,0.0004871537,0.0001421089,0.0004111968,0.00000514542,0.0005816243,0.000003527122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283714,"about_ca_system_score_gemma":0.00005190011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004132715,"about_ca_topic_score_gemma":0.00001517156,"domain_scores_codex":[0.9977472,0.000520083,0.0005009798,0.0004500372,0.0003811761,0.0004005703],"domain_scores_gemma":[0.9986014,0.0002262136,0.000448077,0.0002830006,0.000317127,0.0001241895],"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":[0.0001123266,0.00002800468,0.0001128123,0.00003825957,0.0000911016,0.000003939789,0.0004411284,0.9454861,0.0001592682,0.000242258,0.000002728733,0.05328212],"study_design_scores_gemma":[0.00117705,0.001783256,0.00008631256,0.0001775765,0.00004179279,0.00006555676,0.000126202,0.9959875,0.00002471137,3.13216e-7,0.0003014204,0.0002282916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01090692,0.0003521061,0.9868983,0.00007878843,0.0007392174,0.000765677,8.180486e-7,0.0002292851,0.00002888328],"genre_scores_gemma":[0.9985393,0.00003356736,0.0005840731,0.00003217577,0.0003234045,0.00008598298,0.000004370433,0.00002875924,0.0003683418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876324,"threshold_uncertainty_score":0.9325817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006646327283831069,"score_gpt":0.2161807311212928,"score_spread":0.2095344038374617,"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."}}