Agnostic System Identification for Model-Based Reinforcement Learning

June 2012

Agnostic System Identification for Model-Based Reinforcement Learning

Conference Paper
Proceedings of (ICML) International Conference on Machine Learning

Abstract:

A fundamental problem in control is to learn a model of a system from observations that is useful for controller synthesis. To provide good performance guarantees, existing methods must assume that the real system is in the class of models considered during learning. We present an iterative method with strong guarantees even in the agnostic case where the system is not in the class. In particular, we show that any no-regret online learning algorithm can be used to obtain a near-optimal policy, provided some model achieves low training error and access to a good exploration distribution. Our approach applies to both discrete and continuous domains. We demonstrate its efficacy and scalability on a challenging helicopter domain from the literature
@conference{Ross-2012-7557,
author = {Stephane Ross And J. Andrew (Drew) Bagnell},
title = {Agnostic System Identification for Model-Based Reinforcement Learning},
booktitle = {Proceedings of (ICML) International Conference on Machine Learning},
year = {2012},
month = {June},
pages = {1905 - 1912},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.