Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
复制标题
DOI：
10.1609/aaai.v34i05.6216
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Yuhang Song;Jianyi Wang;Thomas Lukasiewicz;Zhenghua Xu;Mai Xu;Zihan Ding;Lianlong Wu
中科院分区：
文献类型：
--
作者：
Yuhang Song;Jianyi Wang;Thomas Lukasiewicz;Zhenghua Xu;Mai Xu;Zihan Ding;Lianlong Wu
既能参加考试，又能创新的学习智能体正在成为AI领域的热门话题。实现这一愿景的最有希望的途径之一是多代理学习，其中代理充当彼此的环境，而改进每个代理意味着为其他代理提出新的问题。然而，现有的评估平台要么与多智能体设置不兼容，要么局限于特定的游戏。也就是说，目前还没有一个通用的多智能体智能研究评价平台。为此，我们介绍了一个通用的多智能体智能评估平台Arena，它有35个不同逻辑和表示的游戏。此外，多智能体智能还处于许多问题尚未探索的阶段。因此，我们提供了一个构建工具包，供研究人员根据提供的基于图形用户界面可配置的社会树和五个基本多智能体奖励方案的游戏集轻松地发明和构建新的多智能体问题。最后，我们提供了五个最先进的深度多智能体强化学习基线的Python实现。随着基线的实现，我们发布了一组100个最好的代理/团队，我们可以为每个游戏使用不同的培训方案进行培训，作为评估具有种群性能的代理的基础。因此，研究界可以在稳定和统一的标准下进行比较。所有的实现和附带的教程都已在https://sites.google.com/view/arena-unity/.上为社区开源
Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logics and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided game set based on a GUI-configurable social tree and five basic multi-agent reward schemes. Finally, we provide Python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. All the implementations and accompanied tutorials have been open-sourced for the community at https://sites.google.com/view/arena-unity/.