REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES

M. Andrecut () and M. K. Ali ()
Additional contact information
M. Andrecut: Department of Physics, University of Lethbridge, 4401 University Drive, Lethbridge, AB, T1K 3M4, Canada
M. K. Ali: Department of Physics, University of Lethbridge, 4401 University Drive, Lethbridge, AB, T1K 3M4, Canada

International Journal of Modern Physics C (IJMPC), 2004, vol. 15, issue 09, 1235-1247

Abstract: The eligibility trace is the most important mechanism used so far in reinforcement learning to handle delayed reward. Here, we introduce a new kind of eligibility trace, the goal-directed trace, and show that it results in more reliable learning than the conventional trace. In addition, we also propose a new efficient algorithm for solving the goal-directed reinforcement learning problem.

Keywords: Reinforcement learning; prediction; credit assignment (search for similar items in EconPapers)
Date: 2004
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183104006662
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijmpcx:v:15:y:2004:i:09:n:s0129183104006662

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183104006662

Access Statistics for this article

International Journal of Modern Physics C (IJMPC) is currently edited by H. J. Herrmann

More articles in International Journal of Modern Physics C (IJMPC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().