Learning Which Features to Imitate in a Painting Task

摘要

Learning is essential for an autonomous agent to adapt to an environment. One method of learning is through trial and error, however, this method is impractical in a complex environment because of the long learning time required by the agent. Therefore, guidelines are necessary in order to expedite the learning process in such environments, and imitation is one such guideline. Sakato, Ozeki, and Oka (2012) recently proposed a computational model of imitation and autonomous behavior by which an agent can reduce its learning time through imitation. In this paper, we apply the model to a real robot, Nao, and evaluate the model using simple features in a simple environment. We also report on the progress of implementation of the model, and evaluations of the performance of imitation using the implemented model. Our experimental results indicate that the model adapted to the experimental environment by imitation.