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 2005.12360cs.AI
收藏

具有探索Agent的非合作多Agent系统

Non-cooperative Multi-agent Systems with Exploring Agents

Bosch Center for Artificial Intelligence(博世人工智能中心)

Jalal Etesami, Christoph-Nikolas Straehle

摘要:

多智能体学习是机器学习中的一个具有挑战性的问题,它在分布式控制、机器人学和经济学等不同领域都有应用。我们开发了一个规范的多智能体行为模型,使用马尔可夫博弈。由于在许多多代理系统中,代理不一定选择其针对其他代理的最佳策略(例如,多行人互动),我们专注于模型中的代理发挥“探索,但接近最佳的策略”。我们使用Boltzmann-Gibbs分布对这些策略进行建模。这导致了一组耦合的贝尔曼方程,描述了代理的行为。我们引入了一组条件下,一组方程承认一个唯一的解决方案,并提出了两个算法,可证明提供的解决方案,在有限和无限的时间范围的情况下。我们还研究了一个实际的设置,其中的相互作用可以使用占用措施来描述,并提出了一个简化的马尔可夫博弈的复杂性较低。此外,我们建立了探索策略的马尔可夫博弈和多智能体系统的最大因果熵原理之间的联系。最后,我们评估我们的算法的性能,通过几个著名的游戏,从文献和一些游戏,设计的基础上现实世界的应用程序。

英文摘要:

Multi-agent learning is a challenging problem in machine learning that has applications in different domains such as distributed control, robotics, and economics. We develop a prescriptive model of multi-agent behavior using Markov games. Since in many multi-agent systems, agents do not necessary select their optimum strategies against other agents (e.g., multi-pedestrian interaction), we focus on models in which the agents play "exploration but near optimum strategies". We model such policies using the Boltzmann-Gibbs distribution. This leads to a set of coupled Bellman equations that describes the behavior of the agents. We introduce a set of conditions under which the set of equations admit a unique solution and propose two algorithms that provably provide the solution in finite and infinite time horizon scenarios. We also study a practical setting in which the interactions can be described using the occupancy measures and propose a simplified Markov game with less complexity. Furthermore, we establish the connection between the Markov games with exploration strategies and the principle of maximum causal entropy for multi-agent systems. Finally, we evaluate the performance of our algorithms via several well-known games from the literature and some games that are designed based on real world applications.

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。

↑