Factored temporal difference learning in the new ties environment

Gyenes, Viktor and Bontovics, Ákos and Lőrincz, András: Factored temporal difference learning in the new ties environment. Acta cybernetica, (18) 4. pp. 651-668. (2008)

[img] Cikk, tanulmány, mű

Download (993kB)


Although reinforcement learning is a popular method for training an agent for decision making based on rewards, well studied tabular methods are not applicable for large, realistic problems. In this paper, we experiment with a factored version of temporal difference learning, which boils down to a linear function approximation scheme utilising natural features coming from the structure of the task. We conducted experiments in the New Ties environment, which is a novel platform for multi-agent simulations. We show that learning utilising a factored representation is effective even in large state spaces, furthermore it outperforms tabular methods even in smaller problems both in learning speed and stability, because of its generalisation capabilities.

Item Type: Article
Event Title: Symposium of Young Scientists on Intelligent Systems, 2., 2007, Budapest
Journal or Publication Title: Acta cybernetica
Date: 2008
Volume: 18
Number: 4
Page Range: pp. 651-668
ISSN: 0324-721X
Language: angol
Uncontrolled Keywords: Természettudomány, Informatika
Additional Information: Bibliogr.: p. 667-668.; Abstract
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2018. Jun. 05. 14:46
URI: http://acta.bibl.u-szeged.hu/id/eprint/12840

Actions (login required)

View Item View Item