Knowledge Commons of Institute of Automation,CAS
A fuzzy Actor-Critic reinforcement learning network | |
Wang, Xue-Song; Cheng, Yu-Hu; Yi, Jian-Qiang | |
发表期刊 | INFORMATION SCIENCES |
2007-09-15 | |
卷号 | 177期号:18页码:3764-3781 |
文章类型 | Article |
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. |
关键词 | Reinforcement Learning Actor-critic Learning Fuzzy Inference System Radial Basis Function Neural Network |
WOS标题词 | Science & Technology ; Technology |
关键词[WOS] | INFERENCE SYSTEM ; ELEMENTS ; AGENTS ; LOGIC ; RBF |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Information Systems |
WOS记录号 | WOS:000248490400007 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/9407 |
专题 | 09年以前成果 |
通讯作者 | Wang, Xue-Song |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2007 IS - A fuzzy Ac(762KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论