Distributed Policy Gradient for Linear Quadratic Networked Control with Limited Communication Range
This addresses the challenge of efficient control in networked systems with limited communication for applications like robotics or sensor networks, representing an incremental improvement over centralized methods.
The paper tackles the problem of multi-agent linear quadratic networked control under local communication constraints by proposing a scalable distributed policy gradient method, proving its convergence to a near-optimal solution with a performance gap that decreases exponentially as communication and control ranges increase.
This paper proposes a scalable distributed policy gradient method and proves its convergence to near-optimal solution in multi-agent linear quadratic networked systems. The agents engage within a specified network under local communication constraints, implying that each agent can only exchange information with a limited number of neighboring agents. On the underlying graph of the network, each agent implements its control input depending on its nearby neighbors' states in the linear quadratic control setting. We show that it is possible to approximate the exact gradient only using local information. Compared with the centralized optimal controller, the performance gap decreases to zero exponentially as the communication and control ranges increase. We also demonstrate how increasing the communication range enhances system stability in the gradient descent process, thereby elucidating a critical trade-off. The simulation results verify our theoretical findings.