In the last decade, training recurrent neural networks (RNN) using techniques from the area of reservoir computing (RC) became more attractive for learning sequential data due to the ease of network training. Although successfully applied in the language and speech domains, only little is known about using RC techniques for dynamic gesture recognition. We therefore conducted experiments on command gestures using Echo State Networks (ESN) to investigate both the effect of different gesture sequence representations and different parameter configurations. For recognition we employed the ensemble technique, ie using ESN as weak classifiers. Our results show that using ESN is a promising approach for dynamic gesture recognition and we give indications for future experiments.