By Topic

A study on designing controller for peg-pushing robot by using reinforcement learning with adaptive state recruitment strategy

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
2 Author(s)
T. Kondo ; Dept. of Comput. Intelligence & Syst. Sci., Tokyo Inst. of Technol., Japan ; K. Ito

Much attention has been focused on utilizing reinforcement learning (RL) for designing robot controllers. However, as the state spaces of these robots become continuous and high dimensional, it results in time-consuming process. In order to adopt the RL for designing the controllers of such complicated systems, not only adaptability but also computational efficiencies should be taken into account. In this paper, we introduce an adaptive state recruitment strategy, which enables a learning robot to rearrange its state space conveniently according to the task complexity and the progress of the learning.

Published in:

SICE 2003 Annual Conference  (Volume:1 )

Date of Conference:

4-6 Aug. 2003