Neural reinforcement learning for an obstacle avoidance behavior

Abstract

Reinforcement learning (RL) offers a set of various algorithms for in-situation behavior synthesis for robots. The Q-learning technique is certainly the most used of the RL methods. Multilayer perceptron implementations of the Q-learning have been proposed, due to the interest of the restricted memory need and the generalization capability. Self-organizing map implementation of the Q-learning followed. We propose to study the use and discuss the interest of this implementation comparing to a multilayer perceptron implementation or more classical ones. Experiments are performed in the real world with the miniature robot Khepera. (3 pages)