H∞ Optimal Distributed Tracking Control of Network Distributed Systems over Directed Networks via Off-Policy Reinforcement Learning

In this work, an algorithm has been developed for heterogeneous network distributed systems (NDS) communicating over a directed network to solve $H_{\infty}$ optimal distributed tracking control problem of continuous-time systems benefiting off-policy reinforcement learning. It should be noted that recent works on heterogeneous NDS have studied the tracking control problem with decentralized performance functions defined for each subsystem in the network, whereas a global performance function has been defined in this work for the whole NDS. The optimal distributed control problem has been defined as a sequential convex optimization problem benefiting off-policy reinforcement learning with sparsity constraints introduced on the state feedback controller gain. Finally, the efficacy of the proposed algorithm is shown by a numerical simulation on heterogeneous NDS.