This paper presents a novel method for enabling a robot to determine the position of a sound source in three dimensions using just two microphones and interaction with its environment. The method uses the Parameter-Less SelfOrganising Map (PLSOM) algorithm and Reinforcement Learning (RL) to achieve rapid, accurate response. We also introduce a method for directional filtering using the PLSOM. The presented system is compared to a similar system to evaluate its performance. Keywords Active audition