.png){kind=icon}
返回
SURRL: Structural Unsupervised Representations for Robot Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2022.3187186.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Revolutionary advances have occurred in robot learning research, where a resurgence in reinforcement learning (RL) algorithms has fueled breakthroughs in acquiring complicated robotic skills without human intervention. Unfortunately, one limitation that has hampered RL methods is that RL may be quite inefficient, that is, it may cost unrealistic learning time and prohibitively large numbers of trajectories to provide implausible models for achieving multitask learning. In a broader perspective, the realization of robotics control by RL relies heavily on the availability of compact and expressive representations of the state spaces. In this article, we propose to learn vivid general structural representations by utilizing structural prior knowledge of robots. Particularly, a novel framework called structural unsupervised representations for robot learning (SURRL) is presented to enable multitask learning. The task-agnostic sample trajectories are leveraged to learn the structural representations that are constructed by graph autoencoder (GAE) in an unsupervised fashion. When learning a new task, the learned structural representations can be directly adopted for subsequent policy learning without training from scratch. Extensive experiments on continuous robotic environments, including dexterous manipulation tasks, characterize our method's effectiveness to learn optimal policies for handling multiple tasks learning, demonstrating significant improvements over other competitive methods.
Keyword:
Robots
Task analysis
Robot sensing systems
Training
Robot learning
Representation learning
Multitasking
Multitask learning
reinforcement learning (RL)
robotics
structural representations learning
期刊
IF:
4.9
论文数:
1.0K
被引数:
3.5K
机构
引用论文
分享收藏
分享收藏A formal methods approach to interpretable reinforcement learning for robotic planning.png)
SCIENCE ROBOTICS
SCIENCE ROBOTICSIF27.5
PREAI
分享收藏
Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Darwin's mistake: Explaining the discontinuity between human and nonhuman minds达尔文的错误: 解释人类和非人类思想之间的不连续性
PREAI
分享收藏
查看更多内容