McKenzie, Mark

Loxley, Peter

Billingsley, William

Wong, Sebastien

2017

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.

AI 2017: Advances in Artificial Intelligence, 10400(LNAI), p. 14-26

9783319630045

9783319630038

https://hdl.handle.net/1959.11/22116

Springer

Lecture Notes in Computer Science

Competitive reinforcement learning in Atari games

Conference Publication

Publication