This paper investigates a distributed formation tracking control law for large-scale networks of mechanical systems. In particular, the network is represented by directed communication graph with leaders and followers, where each agent described as port-Hamiltonian system constant mass matrix. Moreover, we adopt parameter approach to prove scalable asymptotic stability formation, i.e., scalabil...

Highlighted by success stories like AlphaGo, reinforcement learning (RL) has emerged as a powerful tool for decision making in complex environments. However, the of RL thus far been limited to small-scale or single-agent systems. To apply large-scale networked systems such energy, transportation, and communication networks, critical hurdle is curse dimensionality, because these systems, state a...

We investigate the problem of stabilizing an unknown networked linear system under communication constraints and adversarial disturbances. propose first provably algorithm for problem. The uses a distributed version nested convex body chasing to maintain consistent estimate network dynamics applies level synthesis determine controller based on this estimated model. Our approach avoids need iden...