We study a multi-agent reinforcement learning (MARL) problem where the agents interact
over a given network. The goal of the agents is to cooperatively maximize the average of …

We investigate safe multi-agent reinforcement learning, where agents seek to collectively
maximize an aggregate sum of local objectives while satisfying their own safety constraints …

This paper studies network LQR problems with system matrices being spatially-exponential
decaying (SED) between nodes in the network. The major objective is to study whether the …

Given the success of model-free methods for control design in many problem settings, it is
natural to ask how things will change if realistic communication channels are utilized for the …

Recent advances in model predictive control (MPC) leverage local communication
constraints to produce localized MPC algorithms whose complexities scale independently of …

This paper proposes a scalable distributed policy gradient method and proves its
convergence to near-optimal solution in multi-agent linear quadratic networked systems …

An efficient approach for the construction of separable approximations of optimal value
functions from interconnected optimal control problems is presented. The approach is based …

We consider the distributed control of networked linear time-invariant systems. Previous
work has established the spatial decay property of the centralized controller, which allows …

Distributed optimal control is known to be challenging and can become intractable even for
linear-quadratic regulator problems. In this work, we study a special class of such problems …

This work is primarily concerned about the distributed control of networked linear
timeinvariant (LTI) systems. In particular, we propose a truncated predictive control algorithm …