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 1804.04403math.OC
收藏

潜在博弈中的随机学习:基于沟通和回报的方法

Stochastic Learning in Potential Games: Communication and Payoff-Based Approaches

Tatiana Tatarenko

摘要:

对策论是研究多智能体系统分布式优化问题的有力工具。在本文中,我们考虑多智能体系统,可以通过潜在的游戏,其势函数符合全球目标函数被最大化建模。在这种方法中,智能体对应于战略决策者,最优化问题等价于在设计的博弈中学习势函数最大化器的问题。本文讨论了系统中两种不同的信息设置。首先,我们考虑系统,代理人有机会获得他们的效用函数的梯度。然而,他们并不掌握关于联合行动的全部信息。因此,为了能够沿着梯度向局部最优值移动,它们需要通过通信与它们的邻居交换信息。第二个设置是指一个基于收益的方法来学习势函数最大化。在这里,我们假设在每次迭代代理只能观察自己的行动和经验的回报。在这两种情况下,本文研究了具有可微目标函数的无约束非凸优化问题。为了发展相应的算法,保证收敛到局部最大值的潜在功能的游戏,我们利用著名的Robbins-Monro过程的思想基础上的随机逼近的理论。

英文摘要:

Game theory serves as a powerful tool for distributed optimization in multi-agent systems in different applications. In this paper we consider multi-agent systems that can be modeled by means of potential games whose potential function coincides with a global objective function to be maximized. In this approach, the agents correspond to the strategic decision makers and the optimization problem is equivalent to the problem of learning a potential function maximizer in the designed game. The paper deals with two different information settings in the system. Firstly, we consider systems, where agents have the access to the gradient of their utility functions. However, they do not possess the full information about the joint actions. Thus, to be able to move along the gradient toward a local optimum, they need to exchange the information with their neighbors by means of communication. The second setting refers to a payoff-based approach to learning potential function maximizers. Here, we assume that at each iteration agents can only observe their own played actions and experienced payoffs. In both cases, the paper studies unconstrained non-convex optimization with a differentiable objective function. To develop the corresponding algorithms guaranteeing convergence to a local maximum of the potential function in the game, we utilize the idea of the well-known Robbins-Monro procedure based on the theory of stochastic approximation.

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。

↑