arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1207.4708cs.AI
收藏

The Arcade Learning Environment:一个面向通用代理商的评估平台

The Arcade Learning Environment: An Evaluation Platform for General Agents

University of Alberta(阿尔伯塔大学);Empirical Results Inc.(Empirical Results公司)

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

摘要:

在这篇文章中,我们介绍了街机学习环境(ALE):既是一个挑战性的问题,也是一个评估通用的、独立于领域的人工智能技术发展的平台和方法。ALE为数百个Atari 2600游戏环境提供了一个界面,每个环境都不同,有趣,并且旨在成为人类玩家的挑战。ALE为强化学习、模型学习、基于模型的规划、模仿学习、迁移学习和内在动机提出了重大的研究挑战。最重要的是,它为评估和比较这些问题的方法提供了一个严格的测试平台。我们通过开发和基准测试使用成熟的AI技术设计的独立于领域的代理来说明ALE的前景,这些技术用于强化学习和规划。在这样做的过程中,我们还提出了一个评估方法,通过ALE,报告超过55个不同的游戏的经验结果。所有的软件,包括基准代理,都是公开的。

英文摘要:

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 an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑