Increased learning rates through the sharing of experiences of multiple autonomous mobile robot agents

摘要

This paper describes a reinforcement learning algorithm for small autonomous mobile robot agents based on sets of fuzzy automata. The task of the robots is to learn how to reactively avoid obstacles. In the approach presented two or four robots learn simultaneously, with the experiences of each robot being passed onto the other(s). It is shown that an increasing number of robots sharing their experiences results in a faster and more repeatable learning of each robot's behavioural parameters.