Learning how to do things with imitation
Aris Alissandrakis, Chrystopher L. Nehaniv, Kerstin Dautenhahn · University of Hertfordshire Research Archive (University of Hertfordshire) · 2000
In this paper we discuss how agents can learn to do things by imitating other agents. Especially we look at how the use of different metrics and sub-goal granularity can affect the imitation results. We use a computer model of a chess world as a test-bed to also illustrate issues that arise when there is dissimilar embodiment between the demonstrator and the imitator agents. Introduction Imitation is one of the most important mechanisms whereby knowledge may be transferred and skills acquired between agents (both biological and artificial). It requires two or more agents sharing a context that allows one agent to imitate another. Imitation involves reproducing observed actions and/or effects in an appropriate context. A comprehensive treatment of imitation needs to examine the actions, effects, context and goals of the participating agents. An interdisciplinary framework treating imitation formally is presented in (Nehaniv and Dautenhahn, in press). Most of the imitation literature ...