Improving Reinforcement Learning Speed for Robot Control

Reinforcement learning (R-L) is an intuitive way of programming well-suited for use on autonomous robots because it does not need to specify how the task has to be achieved. However, RL remains difficult to implement in realistic domains because of its slowness in convergence. In this paper, we deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Matignon, L., Laurent, G.J., Le Fort-Piat, N.
Format: Conference Proceeding
Language:English
Subjects:
Control systems
Convergence
Electronic mail
Feedback
Intelligent robots
Learning
Mobile robots
Orbital robotics
Robot control
Robot programming
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reinforcement learning (R-L) is an intuitive way of programming well-suited for use on autonomous robots because it does not need to specify how the task has to be achieved. However, RL remains difficult to implement in realistic domains because of its slowness in convergence. In this paper, we develop a theoretical study of the influence of some RL parameters over the learning speed. We also provide experimental justifications for choosing the reward function and initial Q-values in order to improve RL speed within the context of a goal-directed robot task
ISSN:2153-0858
2153-0866
DOI:10.1109/IROS.2006.282341