Learning interface agents

It is argued that the machine learning approach to building interface agents is a feasible one which has several advantages over other approaches: it provides a customized and adaptive solution which is less costly and ensures better user acceptability.

Abstract

Interface agents are computer programs that employ Artificial Intelligence techniques in order to provide assistance to a user dealing with a particular comput-er application. The paper discusses an interface agent which has been modelled closely after the metaphor of a personal assistant. The agent learns how to as-sist the user by (i) observing the user’s actions and imitating them, (ii) receiving user feedback when it takes wrong actions and (iii) being trained by the us-er on the basis of hypothetical examples. The paper discusses how this learning agent was implemented us-ing memory-based learning and reinforcement learning techniques. It presents actual results from two proto-type agents built using these techniques: one for a meeting scheduling application and one for electronic mail. It argues that the machine learning approach to building interface agents is a feasible one which has several advantages over other approaches: it provides a customized and adaptive solution which is less cost-ly and ensures better user acceptability. The paper also argues what the advantages are of the particular learning techniques used.