Learning to Transform Service Instructions into Actions with Reinforcement Learning and Knowledge Base
文献类型：期刊论文
| 作者 | Meng-Yang Zhang1,2; Guo-Hui Tian1,2; Ci-Ci Li1,2; Jing Gong2 |
| 刊名 | International Journal of Automation and Computing
 |
| 出版日期 | 2018 |
| 卷号 | 15期号:5页码:582-592 |
| 关键词 | Natural language robot knowledge base reinforcement learning object state. |
| ISSN号 | 1476-8186 |
| DOI | 10.1007/s11633-018-1128-9 |
| 英文摘要 | In order to improve the learning ability of robots, we present a reinforcement learning approach with a knowledge base for mapping natural language instructions to executable action sequences. A simulated platform with physical engine is built as interactive environment. Based on the knowledge base, a reward function with immediate rewards and delayed rewards is designed to handle sparse reward problems. Also, a list of object states is produced by retrieving the knowledge base, as a standard to define the quality of action sequences. Experimental results demonstrate that our approach yields good performance on accuracy of action sequences production. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/42435]  |
| 专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
| 作者单位 | 1.Shenzhen Research Institute, Shandong University, Shenzhen 518000, China 2.School of Control Science and Engineering, Shandong University, Jinan 253000, China |
| 推荐引用方式 GB/T 7714 | Meng-Yang Zhang,Guo-Hui Tian,Ci-Ci Li,et al. Learning to Transform Service Instructions into Actions with Reinforcement Learning and Knowledge Base[J]. International Journal of Automation and Computing,2018,15(5):582-592. |
| APA | Meng-Yang Zhang,Guo-Hui Tian,Ci-Ci Li,&Jing Gong.(2018).Learning to Transform Service Instructions into Actions with Reinforcement Learning and Knowledge Base.International Journal of Automation and Computing,15(5),582-592. |
| MLA | Meng-Yang Zhang,et al."Learning to Transform Service Instructions into Actions with Reinforcement Learning and Knowledge Base".International Journal of Automation and Computing 15.5(2018):582-592. |
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。