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 1902.04043cs.LGcs.MAstat.ML
收藏

StarCraft多智能体挑战

The StarCraft Multi-Agent Challenge

Russian-Armenian University(俄罗斯-亚美尼亚大学);University of Oxford(牛津大学);Facebook AI Research(脸书人工智能研究院)
Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foer… 展开作者

Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foerster, Shimon Whiteson

摘要:

在过去的几年里,深度多智能体强化学习(RL)已经成为一个非常活跃的研究领域。在这一领域,一个特别具有挑战性的问题是部分可观察的,合作的,多智能体学习,其中代理团队必须学会协调他们的行为,同时仅以他们的私人观察为条件。这是一个有吸引力的研究领域,因为这样的问题是相关的大量的现实世界中的系统,也更适合于评估比一般和问题。ALE和MuJoCo等标准化环境允许单代理RL超越玩具领域,如网格世界。然而,合作多智能体RL没有可比的基准。因此,该领域的大多数论文都使用一次性的玩具问题,难以衡量实际进展。在本文中,我们提出了星际争霸多智能体挑战赛(SMAC)作为一个基准问题,以填补这一空白。SMAC基于流行的实时战略游戏《星际争霸II》,专注于微观管理挑战,其中每个单元都由一个独立的代理控制,必须根据本地观察采取行动。我们为基准测试和评估的最佳实践提供了一套多样化的挑战地图和建议。我们还开源了一个深度多代理RL学习框架,包括最先进的算法。我们相信SMAC可以在未来几年提供一个标准的基准环境。我们最好的代理人的几个SMAC方案的视频可在:www.example.com.

英文摘要:

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

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。

↑