caa a22 4500 606159711 CHVBK 20210128100626.0 cr unu---uuuuu 210128e20150501xx s 000 0 eng 10.1007/s00521-014-1738-2 doi (NATIONALLICENCE)springer-10.1007/s00521-014-1738-2 A data-based online reinforcement learning algorithm satisfying probably approximately correct principle [Elektronische Daten] [Yuanheng Zhu, Dongbin Zhao] This paper proposes a probably approximately correct (PAC) algorithm that directly utilizes online data efficiently to solve the optimal control problem of continuous deterministic systems without system parameters for the first time. The dependence on some specific approximation structures is crucial to limit the wide application of online reinforcement learning (RL) algorithms. We utilize the online data directly with the kd-tree technique to remove this limitation. Moreover, we design the algorithm in the PAC principle. Complete theoretical proofs are presented, and three examples are simulated to verify its good performance. It draws the conclusion that the proposed RL algorithm specifies the maximum running time to reach a near-optimal control policy with only online data. The Natural Computing Applications Forum, 2014 Reinforcement learning nationallicence Probably approximately correct nationallicence Kd-tree nationallicence Zhu Yuanheng The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China aut Zhao Dongbin The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China aut Neural Computing and Applications Springer London 26/4(2015-05-01), 775-787 0941-0643 26:4<775 2015 26 521 https://doi.org/10.1007/s00521-014-1738-2 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1738-2 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Zhu Yuanheng The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China aut NATIONALLICENCE 700 1- Zhao Dongbin The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/4(2015-05-01), 775-787 0941-0643 26:4<775 2015 26 521