Learning Control Composition in aComplex

In this paper, reinforcement learning algorithms are applied to a foraging task, expressed as a control composition problem. The domain used is a simulated world in which a variety of creatures (agents) live and interact, reacting to stimuli and to each other. In such dynamic, uncertain environments , fast adaptation is important, and there is a need for new architectures that facilitate on-line learning. Recently, control composition has shown its potential in reducing the complexity of learning in many domains, permitting more complex tasks to be addressed. Results presented here restate the above claim and also show that the use of a modiied version of the Q-learning algorithm performs better in the non-Markovian sequential decision task proposed. In addition, it is shown that shaping can be successfully used to improve the performance of these learning algorithms in complex environments.