Competitive reinforcement learning in Atari games

Author(s)
McKenzie, Mark
Loxley, Peter
Billingsley, William
Wong, Sebastien
Publication Date
2017
Abstract
This research describes a study into the ability of a state of the art reinforcement learning algorithm to learn to perform multiple tasks. We demonstrate that the limitation of learning to performing two tasks can be mitigated with a competitive training method. We show that this approach results in improved generalization of the system when performing unforeseen tasks. The learning agent assessed is an altered version of the DeepMind deep Q–learner network (DQN), which has been demonstrated to outperform human players for a number of Atari 2600 games. The key findings of this paper is that there were significant degradations in performance when learning more than one game, and how this varies depends on both similarity and the comparative complexity of the two games.
Citation
AI 2017: Advances in Artificial Intelligence, 10400(LNAI), p. 14-26
ISBN
9783319630045
9783319630038
Link
Publisher
Springer
Series
Lecture Notes in Computer Science
Title
Competitive reinforcement learning in Atari games
Type of document
Conference Publication
Entity Type
Publication

Files:

NameSizeformatDescriptionLink