Multi-target tracking using a compact Q-learning with a teacher

This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Real and simulated experiments using the well-known robot simulator Webots on a proof of context both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the overall system performance.