Knowledge Commons of Institute of Automation,CAS
Manipulation Skill Learning on Multi-step Complex Task Based on Explicit and Implicit Curriculum Learning | |
Liu, Naijun1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | SCIENCE CHINA Information Sciences
![]() |
ISSN | 1674-733X |
2020 | |
卷号 | 0期号:0页码:0-0 |
通讯作者 | Lu, Tao(tao.lu@ia.ac.cn) |
摘要 | Deep reinforcement learning can endow robot agents with the ability to learn manipulation skills with promising performance. However, manipulation skills learning on complicated tasks poses great challenges due to higher exploration of state-action space and uninformative sparse rewards. To address the challenges in manipulation skill learning on multi-step complex tasks and overcome the limitation of current methods, we propose an efficient curriculum learning method called Task Auxiliary and Task Difficulty-HER (TATD-HER), which is endowed with a high-low level curriculum learning structure and combines the explicit and implicit curriculum learning mechanisms together for policy training. The experimental results show that the proposed learning paradigm has the capability of achieving satisfactory performance in manipulation skill learning on multi-step complicated task. |
关键词 | robot manipulation skill learning multi-step complex task curriculum learning |
DOI | 10.1007/s11432-019-2648-7 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61773378] ; National Natural Science Foundation of China[U1713222] ; National Natural Science Foundation of China[U1806204] ; Equipment Pre-research Field Fund[61403120407] |
项目资助者 | National Natural Science Foundation of China ; Equipment Pre-research Field Fund |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Information Systems ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000656946500001 |
出版者 | SCIENCE PRESS |
七大方向——子方向分类 | 智能机器人 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40455 |
专题 | 复杂系统认知与决策实验室_先进机器人 多模态人工智能系统全国重点实验室_机器人理论与应用 |
作者单位 | 1.Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
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 | Liu, Naijun,Lu, Tao,Cai, Yinghao,et al. Manipulation Skill Learning on Multi-step Complex Task Based on Explicit and Implicit Curriculum Learning[J]. SCIENCE CHINA Information Sciences,2020,0(0):0-0. |
APA | Liu, Naijun,Lu, Tao,Cai, Yinghao,Wang, Rui,&Wang, Shuo.(2020).Manipulation Skill Learning on Multi-step Complex Task Based on Explicit and Implicit Curriculum Learning.SCIENCE CHINA Information Sciences,0(0),0-0. |
MLA | Liu, Naijun,et al."Manipulation Skill Learning on Multi-step Complex Task Based on Explicit and Implicit Curriculum Learning".SCIENCE CHINA Information Sciences 0.0(2020):0-0. |
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 | ||
s11432-019-2648-.pdf(2456KB) | 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