论文标题
遗憾的最小化方法来控制多代理控制
A Regret Minimization Approach to Multi-Agent Control
论文作者
论文摘要
我们研究具有已知动力学和对抗性干扰的动态系统多代理控制的问题。我们的研究专注于没有集中预先计算的策略的最佳控制，而是针对只配备稳定控制器的不同代理的自适应控制策略。我们从任何（标准）遗憾最大程度地减少控制方法到分布式算法的降低。减少保证，相对于最佳预先计算的联合政策，所得的分布式算法对此感到遗憾。我们的方法涉及将在线凸优化概括为多代理设置，并应用为单个代理提供的非固定控制的最新工具。我们在验证飞机过度的模型上经验评估了我们的方法。我们表明，分布式方法对失败和动力学中的对抗扰动是可靠的。
We study the problem of multi-agent control of a dynamical system with known dynamics and adversarial disturbances. Our study focuses on optimal control without centralized precomputed policies, but rather with adaptive control policies for the different agents that are only equipped with a stabilizing controller. We give a reduction from any (standard) regret minimizing control method to a distributed algorithm. The reduction guarantees that the resulting distributed algorithm has low regret relative to the optimal precomputed joint policy. Our methodology involves generalizing online convex optimization to a multi-agent setting and applying recent tools from nonstochastic control derived for a single agent. We empirically evaluate our method on a model of an overactuated aircraft. We show that the distributed method is robust to failure and to adversarial perturbations in the dynamics.
