Optimisation with Zeroth-Order Oracles in Formation

Abstract

In this paper, we consider the optimisation of time varying functions by a network of agents with no gradient information. We propose a novel method to estimate the gradient at each agent's position using only neighbour information. The gradient estimation is coupled with a formation controller, to minimise gradient estimation error and prevent agent collisions. Convergence results for the algorithm are provided for functions which satisfy the Polyak-Lojasiewicz inequality. Simulations and numerical results are provided to support the theoretical results.