学习用高斯过程时间差分法控制八达通臂Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods |
|
课程网址: | http://videolectures.net/gpip06_engel_lcoag/ |
主讲教师: | Yaakov Engel |
开课单位: | 阿尔伯塔大学 |
开课时间: | 2007-02-25 |
课程语种: | 英语 |
中文简介: | 八达通手臂是一个多功能和复杂的肢体。八爪鱼如何控制这种超冗余臂(更不用说其中的八个!)尚不得而知。基于相同机械原理的机械臂可能使当今的机器人手臂过时。在本次演讲中,我将描述我们如何使用在线强化学习算法来解决这个问题,该算法基于贝叶斯策略评估方法,称为高斯过程时间差(GPTD)学习。 |
课程简介: | The Octopus arm is a highly versatile and complex limb. How the Octopus controls such a hyper-redundant arm (not to mention eight of them!) is as yet unknown. Robotic arms based on the same mechanical principles may render present day robotic arms obsolete. In this talk, I will describe how we tackle this problem using an online reinforcement learning algorithm, based on a Bayesian approach to policy evaluation known as Gaussian process temporal difference (GPTD) learning. |
关 键 词: | 八达通手臂; 超冗余臂; 机械原理 |
课程来源: | 视频讲座网 |
最后编审: | 2019-04-15:cwx |
阅读次数: | 57 |