Learning Individual Features to Decompose State Space for Robotic Skill Learning
文献类型:会议论文
作者 | Fengyi Zhang2,3![]() ![]() ![]() |
出版日期 | 2020-08 |
会议日期 | 2020-8 |
会议地点 | Online |
关键词 | Robotic Skill Learning Graph Neural Networks State Decomposition |
英文摘要 | Due to suffering from the diversity and complexity of robotic tasks in continuous domains, robotic skill learning is the most challenging issue in this area, especially for robots with high-dimensional state spaces. To learn structured policies for continuous control, the graph neural networks (GNN) was previously applied to incorporate explicitly the robot structure into the policy network. In this work, we tackle the problem of robotic skill learning in high-dimensional state space with the help of graph neural networks. Instead of utilizing a general purpose multi-layer perceptron (MLP) as a unified controller to output actions for all joints of the robot, we construct a separate controller for each joint of the robot by using the individual features that have been extracted by GNN model. Empirical results on simulated continuous systems, including applications to PR2 task and Centipede task, demonstrate that the proposed framework can achieve satisfactory learning performance, and more importantly, it significantly reduces the parameters of the policy network. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/50843] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
通讯作者 | Zhiyong Liu |
作者单位 | 1.CAS Centre for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China 3.State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China |
推荐引用方式 GB/T 7714 | Fengyi Zhang,Fangzhou Xiong,Zhiyong Liu. Learning Individual Features to Decompose State Space for Robotic Skill Learning[C]. 见:. Online. 2020-8. |
入库方式: OAI收割
来源:自动化研究所
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。