Knowledge Commons of Institute of Automation,CAS
Parallel reinforcement learning: a framework and case study | |
Teng Liu1; Bin TIan1; Yunfeng Ai2; Li Li3; Dongpu Cao4; Feiyue Wang1 | |
发表期刊 | IEEE/CAA Journal of Automatica Sinica |
2018-07 | |
卷号 | 5期号:4页码:827-835 |
摘要 | In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain (MC) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced. |
收录类别 | SCI |
七大方向——子方向分类 | 人工智能+交通 |
国重实验室规划方向分类 | 虚实融合与迁移学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51628 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 3.清华大学 4.滑铁卢大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Teng Liu,Bin TIan,Yunfeng Ai,et al. Parallel reinforcement learning: a framework and case study[J]. IEEE/CAA Journal of Automatica Sinica,2018,5(4):827-835. |
APA | Teng Liu,Bin TIan,Yunfeng Ai,Li Li,Dongpu Cao,&Feiyue Wang.(2018).Parallel reinforcement learning: a framework and case study.IEEE/CAA Journal of Automatica Sinica,5(4),827-835. |
MLA | Teng Liu,et al."Parallel reinforcement learning: a framework and case study".IEEE/CAA Journal of Automatica Sinica 5.4(2018):827-835. |
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 | ||
2018-JAS-Parallel Re(7005KB) | 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