Factored temporal difference learning in the new ties environment

  • Viktor Gyenes
  • Ákos Bontovics
  • András Lőrincz

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.

Downloads

Download data is not yet available.
Published
2008-01-01
How to Cite
Gyenes, V., Bontovics, Ákos, & Lőrincz, A. (2008). Factored temporal difference learning in the new ties environment. Acta Cybernetica, 18(4), 651-668. Retrieved from https://cyber.bibl.u-szeged.hu/index.php/actcybern/article/view/3743
Section
Regular articles