Towards imitation-enhanced Reinforcement Learning in multi-agent systems
Mehmet Dinçer Erbaş, Alan F. T. Winfield, Larry Bull · 2011
Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning learn faster than those with Q-learning alone.