Search Machine Learning Repository:
Online Multi-Task Learning for Policy Gradient Methods
Authors: Haitham B. Ammar, Eric Eaton, Paul Ruvolo and Matthew Taylor
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: Policy gradient algorithms have shown considerable recent success in solving high-dimensional sequential decision making tasks, particularly in robotics. However, these methods often require extensive experience in a domain to achieve high performance. To make agents more sample-efficient, we developed a multi-task policy gradient method to learn decision making tasks consecutively, transferring knowledge between tasks to accelerate learning. Our approach provides robust theoretical guarantees, and we show empirically that it dramatically accelerates learning on a variety of dynamical systems, including an application to quadrotor control.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).