Proceedings

The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract)

Marc G. Bellemare, Yavar Naddaf, Joel Veness, Michael H. Bowling

Download BibTeX Cite

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Journal Track. Pages 4148-4151.

Abstract

In this extended abstract we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by presenting a benchmark set of domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. We conclude with a brief update on the latest ALE developments. All of the software, including the benchmark agents, is publicly available.

Marc G. Bellemare, Yavar Naddaf, Joel Veness, and Michael H. Bowling. 2015. The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract). In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15. IJCAI, 4148–4151. https://ijcai.org/proceedings/2015/585
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards