{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001045231,0.0007795766,0.0007809232,0.0003100194,0.0003958743,0.0006705157,0.00069733,0.0007651972,0.001079253],"category_scores_gemma":[0.002504976,0.0003180102,0.0003203713,0.0002273841,0.001078282,0.0006057007,0.001197829,0.0008087049,0.0001313544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007417836,"about_ca_system_score_gemma":0.0008548725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005544028,"about_ca_topic_score_gemma":0.002700029,"domain_scores_codex":[0.9996634,0.0001135174,0.0000162377,0.00006977523,0.00007642275,0.00006076212],"domain_scores_gemma":[0.9989974,0.0005572347,0.0001902686,0.00005338686,0.0001419264,0.00005978646],"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":[0.00005746921,0.00002746155,0.0004048295,0.00003532256,0.00001853784,0.00007508255,0.00005946813,0.9829317,0.001358934,0.006669716,0.000165782,0.008195774],"study_design_scores_gemma":[0.000008151831,0.00001909289,0.00003933742,0.000002504948,0.000002415972,0.000003978049,0.000004253622,0.9982402,0.0001898769,0.001414103,0.00007421057,0.000001903425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1068509,0.0002888416,0.8865497,0.0003478783,0.00005447443,0.00007212658,0.00002274517,0.0003370665,0.005476264],"genre_scores_gemma":[0.9884673,0.0000512156,0.01031099,0.00004172329,0.000009900402,0.00005205101,0.00001256465,0.00001197844,0.001042263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005544028,"threshold_uncertainty_score":0.01102352,"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."}}