The Arcade Learning Environment: An Evaluation Platform for General Agents. Bellemare, M. G, Naddaf, Y., Veness, J., & Bowling, M. arXiv.org, cs.AI, 2012.
abstract   bibtex   
In this article 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 developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose a methodology for evaluation made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.
@Article{Bellemare2012,
author = {Bellemare, Marc G and Naddaf, Yavar and Veness, Joel and Bowling, Michael}, 
title = {The Arcade Learning Environment: An Evaluation Platform for General Agents}, 
journal = {arXiv.org}, 
volume = {cs.AI}, 
number = {}, 
pages = {}, 
year = {2012}, 
abstract = {In this article 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 developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose a methodology for evaluation made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.}, 
location = {}, 
keywords = {}}

Downloads: 0