Blending Autonomous Exploration and Apprenticeship Learning
Thomas J. Walsh, Daniel Hewlett, Clayton T. Morrison · 2011
We present theoretical and empirical results for a framework that combines the benefits of apprenticeship and autonomous reinforcement learning. Our approach modifies an existing apprenticeship learning framework that relies on teacher demonstrations and does not necessarily explore the environment. The first change is replacing previously used Mistake Bound model learners with a recently pro-posed framework that melds the KWIK and Mistake Bound supervised learning protocols. The second change is introducing a communication of expected util-ity from the student to the teacher. The resulting system only uses teacher traces when the agent needs to learn concepts it cannot efficiently learn on its own. 1