Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control
文献类型：期刊论文
| 作者 | Wang JP(王军平)
|
| 刊名 | IEEE Transaction on Industrial Informatics
 |
| 出版日期 | 2017-09 |
| 期号 | 27页码:1-9 |
| 关键词 | Industry 4.0 Distributed Coordination Control Multi-task Generative Adversarial Nets Decision Making |
| 英文摘要 | Generating sequential decision policy from huge amounts of measured process data is a novel research direction for collaborative factory automation, making full use of those online or offline process data to directly design flexible make decisions policy, and evaluate performance. The key challenges for the cross-domain sequential decision process is to online generate sequential decision making policy directly, and transferring knowledge between tasks. Most multi-task policy generating algorithms often suffer from insufficient generating cross-task sharing structure at discrete-time nonlinear systems with applications. This paper proposes the multi-task generative adversarial nets with shared memory for cross-Domain coordination control, which can generate sequential decision policy directly from raw sensory input of all of tasks, and online evaluate performance of system actions in discrete-time nonlinear systems. Experiments on three groups of discrete-time nonlinear control tasks show that our proposed model can availably improve the performance of task with the help of other related tasks. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/15467]  |
| 专题 | 精密感知与控制研究中心_人工智能与机器学习 |
| 推荐引用方式 GB/T 7714 | Wang JP. Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control[J]. IEEE Transaction on Industrial Informatics,2017(27):1-9. |
| APA | Wang JP.(2017).Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control.IEEE Transaction on Industrial Informatics(27),1-9. |
| MLA | Wang JP."Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control".IEEE Transaction on Industrial Informatics .27(2017):1-9. |
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。