A fuzzy Actor-Critic reinforcement learning network
文献类型：期刊论文
| 作者 | Wang, Xue-Song; Cheng, Yu-Hu; Yi, Jian-Qiang
|
| 刊名 | INFORMATION SCIENCES
 |
| 出版日期 | 2007-09-15 |
| 卷号 | 177期号:18页码:3764-3781 |
| 关键词 | reinforcement learning Actor-Critic learning fuzzy inference system radial basis function neural network |
| 通讯作者 | Wang, Xue-Song |
| 英文摘要 | One of the difficulties encountered in the application of reinforcement learning methods to real-world problems is their limited ability to cope with large-scale or continuous spaces. In order to solve the curse of the dimensionality problem, resulting from making continuous state or action spaces discrete, a new fuzzy Actor-Critic reinforcement learning network (FACRLN) based on a fuzzy radial basis function (FRBF) neural network is proposed. The architecture of FACRLN is realized by a four-layer FRBF neural network that is used to approximate both the action value function of the Actor and the state value function of the Critic simultaneously. The Actor and the Critic networks share the input, rule and normalized layers of the FRBF network, which can reduce the demands for storage space from the learning system and avoid repeated computations for the outputs of the rule units. Moreover, the FRBF network is able to adjust its structure and parameters in an adaptive way with a novel self-organizing approach according to the complexity of the task and the progress in learning, which ensures an economic size of the network. Experimental studies concerning a cart-pole balancing control illustrate the performance and applicability of the proposed FACRLN. (C) 2007 Elsevier Inc. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Information Systems |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | INFERENCE SYSTEM ; ELEMENTS ; AGENTS ; LOGIC ; RBF |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000248490400007 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/9407]  |
| 专题 | 自动化研究所_09年以前成果 |
| 作者单位 | 1.China Univ Mining & Technol, Sch Informat & Elect Engn, Xuzhou 221008, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Automat, Lab Complex Syst & Intelligence Sci, Beijing 100080, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Xue-Song,Cheng, Yu-Hu,Yi, Jian-Qiang. A fuzzy Actor-Critic reinforcement learning network[J]. INFORMATION SCIENCES,2007,177(18):3764-3781. |
| APA | Wang, Xue-Song,Cheng, Yu-Hu,&Yi, Jian-Qiang.(2007).A fuzzy Actor-Critic reinforcement learning network.INFORMATION SCIENCES,177(18),3764-3781. |
| MLA | Wang, Xue-Song,et al."A fuzzy Actor-Critic reinforcement learning network".INFORMATION SCIENCES 177.18(2007):3764-3781. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。