Encoding Intelligent Agents for Uncertain, Unknown, and Dynamic Tasks: From Programming to Interactive Artificial Learning

Jacob W. Crandall, Michael A. Goodrich, Lanny Lin

In this position paper, we analyze ways that a human can best be involved in interactive artificial learning against a backdrop of traditional AI programming and conventional artificial learning. Our primary claim is that interactive artificial learning can produce a higher return on human investment than conventional methods, meaning that performance of the agent exceeds performance of traditional agents at a lower cost to the human. This claim is clarified by identifying metrics that govern the effectiveness of interactive artificial learning. We then present a roadmap for achieving this claim, identifying ways in which interactive artificial learning can be used to improve each stage of training an artificial agent: configuring, planning, acting, observing, and updating. We conclude by presenting a case study that contrasts programming using conventional artificial learning to programming using interactive artificial learning.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.