Propagation Networks for Model-Based Control Under Partial Observation

May 2019

Propagation Networks for Model-Based Control Under Partial Observation

Authors:

Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, and Russ Tedrake
Conference Paper
Proceedings of (ICRA) International Conference on Robotics and Automation

Abstract:

There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. With these innovations, our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks. Compared with existing deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to novel, partially observable scenes and tasks.
@conference{Li-2019-125681,
author = {Yunzhu Li And Jiajun Wu And Jun-Yan Zhu And Joshua B. Tenenbaum And Antonio Torralba And Russ Tedrake},
title = {Propagation Networks for Model-Based Control Under Partial Observation},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2019},
month = {May},
pages = {1205 - 1211},
}
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.