Gyenes Viktor and Bontovics Ákos and Lőrincz András: Factored temporal difference learning in the new ties environment. In: Acta cybernetica, (18) 4. pp. 651-668. (2008)
Preview |
Cikk, tanulmány, mű
Gyenes_2008_ActaCybernetica.pdf Download (993kB) | Preview |
Abstract
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 |
|---|---|
| Journal or Publication Title: | Acta cybernetica |
| Date: | 2008 |
| Volume: | 18 |
| Number: | 4 |
| ISSN: | 0324-721X |
| Page Range: | pp. 651-668 |
| Language: | English |
| Place of Publication: | Szeged |
| Event Title: | Symposium of Young Scientists on Intelligent Systems (2.) (2007) (Budapest) |
| Related URLs: | http://acta.bibl.u-szeged.hu/38526/ |
| Uncontrolled Keywords: | Számítástechnika, Kibernetika |
| Additional Information: | Bibliogr.: p. 667-668. ; összefoglalás angol nyelven |
| Subjects: | 01. Natural sciences 01. Natural sciences > 01.02. Computer and information sciences |
| Date Deposited: | 2016. Oct. 15. 12:25 |
| Last Modified: | 2022. Jun. 16. 14:51 |
| URI: | http://acta.bibl.u-szeged.hu/id/eprint/12840 |
Actions (login required)
 |
View Item |
