Robot shaping: developing autonomous agents through learning

摘要

Learning plays a vital role in the development of autonomous agents. In this paper, we explore the use of reinforcement learning to “shape” a robot to perform a predefined target behavior. We connect both simulated and real robots to Alecsys, a parallel implementation of a learning classifier system with an extended genetic algorithm. After classifying different kinds of Animat-like behaviors, we explore the effects on learning of different types of agent's architecture and training strategies. We show that the best results are achieved when both the agent's architecture and the training strategy match the structure of the behavior pattern to be learned. We report the results of a number of experiments carried out both in simulated and in real environments, and show that the results of simulations carry smoothly to physical robots. While most of our experiments deal with simple reactive behavior, in one of them we demonstrate the use of a simple and general memory mechanism. As a whole, our experimental activity demonstrates that classifier systems with genetic algorithms can be practically employed to develop autonomous agents.