Framework for robot skill learning using reinforcement learning

Yingzi Wei; Mingyang Zhao

doi:10.1117/12.522188

2 September 2003 Framework for robot skill learning using reinforcement learning

Yingzi Wei, Mingyang Zhao

Proceedings Volume 5253, Fifth International Symposium on Instrumentation and Control Technology; (2003) https://doi.org/10.1117/12.522188
Event: Fifth International Symposium on Instrumentation and Control Technology, 2003, Beijing, China

Abstract

Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is an on-line actor critic method for a robot to develop its skill. The reinforcement function has become the critical component for its effect of evaluating the action and guiding the learning process. We present an augmented reward function that provides a new way for RL controller to incorporate prior knowledge and experience into the RL controller. Also, the difference form of augmented reward function is considered carefully. The additional reward beyond conventional reward will provide more heuristic information for RL. In this paper, we present a strategy for the task of complex skill learning. Automatic robot shaping policy is to dissolve the complex skill into a hierarchical learning process. The new form of value function is introduced to attain smooth motion switching swiftly. We present a formal, but practical, framework for robot skill learning and also illustrate with an example the utility of method for learning skilled robot control on line.

Citation Download Citation

Yingzi Wei and Mingyang Zhao "Framework for robot skill learning using reinforcement learning", Proc. SPIE 5253, Fifth International Symposium on Instrumentation and Control Technology, (2 September 2003); https://doi.org/10.1117/12.522188

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available