Dialogue management optimisation has been cast into a planning under uncertainty problem for long. Some methods such as Reinforcement Learning (RL) are now part of the state of the art. Whatever the solving method, strong assumptions are made about the dialogue system properties. For instance, RL assumes that the dialogue state space is Markovian. Such constraints may involve important engineering work. This paper introduces a more general approach, based on fewer modelling assumptions. A Black Box Optimisation (BBO) method and more precisely a Particle Swarm Optimisation (PSO) is used to solve the control problem. In addition, PSO allows taking advantage of the parallel aspect of the problem of optimising a system online with many users calling at the same time. Some preliminary results are presented.