Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this article we take a big picture look at how the ALE is being used by the research community. We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE. We use this discussion to present some methodological best practices and provide new benchmark results using these best practices. To further the progress in the field, we introduce a new version of the ALE that supports multiple game modes and provides a form of stochasticity we call sticky actions. We conclude this big picture look by revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.
Citation
M. Machado,
M. Bellemare,
E. Talvitie,
J. Veness,
M. Hausknecht,
M. Bowling.
"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents".
Journal of Artificial Intelligence Research (JAIR), 61, pp 523-562, March 2018.
| Keywords: |
|
| Category: |
In Journal |
| Web Links: |
JAIR |
| |
DOI |
BibTeX
@article{Machado+al:JAIR18,
author = {Marlos Machado and Marc Bellemare and Erik Talvitie and Joel Veness
and Matthew Hausknecht and Michael Bowling},
title = {Revisiting the Arcade Learning Environment: Evaluation Protocols and
Open Problems for General Agents},
Volume = "61",
Pages = {523-562},
journal = {Journal of Artificial Intelligence Research (JAIR)},
year = 2018,
}Last Updated: February 24, 2020
Submitted by Sabina P 
