Kernel-based learning with guarantees for multi-agent applications

A multi-agent system is a network of autonomous entities called agents that share information and collaborate to solve tasks usually beyond an individual agent's scope [12]. This broad description fits well in the recent research trends like cloud computing [11], or Industry 4.0 [10], and allows multi-agent systems to find applications in many other fields. In robotics, in scenarios including groups of mobile robots or swarms of drones, it is necessary to avoid collisions or obstacles and to navigate collaboratively [9]. The agent-based approach is also used for controlling smart grids, i.e., efficient and robust power systems [6]. We can also find numerous other examples, like analyzing the traffic flow [7] or modelling purchasing decisions [3]. Inspired by these multidisciplinary applications, we formally discuss the general problem of distributed learning, with a particular focus on the modelling of nonlinearities under limited information, cf.