Scheduled System Maintenance:
On Monday, April 27th, IEEE Xplore will undergo scheduled maintenance from 1:00 PM - 3:00 PM ET (17:00 - 19:00 UTC). No interruption in service is anticipated.
By Topic

Automatic generation of macro-actions using genetic algorithm for reinforcement learning

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.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Tateyama, T. ; Graduate Sch. of Eng., Tokyo Metropolitan Univ., Japan ; Kawata, S. ; Oguchi, T.

The main problem of reinforcement learning is that the learning converges slowly. As one of the solutions, McGovern (1997) proposed the "macro-action". However, a human expert needs to design macro-actions which adapt to an environment. In this paper, we propose a new method that enables one to generate the macro-actions which adapt to the environment automatically using the genetic algorithm.

Published in:

SICE 2002. Proceedings of the 41st SICE Annual Conference  (Volume:1 )

Date of Conference:

5-7 Aug. 2002