State of the art control of atari games using shallow reinforcement learning
The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underlie DQN's impressive performance and to better contextualize its success. We systematically evaluate the importance of key representational biases encoded by DQN's network by proposing simple linear representations that make use of these concepts. Incorporating these characteristics, we obtain a computationally practical feature set that achieves competitive performance to DQN in the ALE. Besides offering insight into the strengths and weaknesses of DQN, we provide a generic representation for the ALE, significantly reducing the burden of learning a representation for each game. Moreover, we also provide a simple, reproducible benchmark for the sake of comparison to future work in the ALE.
Citation
Y. Liang,
M. Machado,
E. Talvitie,
M. Bowling.
"State of the art control of atari games using shallow reinforcement learning". Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), (ed: Catholijn M. Jonker, Stacy Marsella, John Thangarajah, Karl Tuyls), pp 485-493, May 2016.
BibTeX
@incollection{Liang+al:AAMAS16,
author = {Yitao Liang and Marlos Machado and Erik Talvitie and Michael
Bowling},
title = {State of the art control of atari games using shallow reinforcement
learning},
Editor = {Catholijn M. Jonker, Stacy Marsella, John Thangarajah, Karl Tuyls},
Pages = {485-493},
booktitle = {Joint Conference on Autonomous Agents and Multi-Agent Systems
(AAMAS)},
year = 2016,
}Last Updated: October 28, 2020
Submitted by Sabina P 
