Propagation Networks for Model-Based Control Under Partial Observation


Yunzhu Li      Jiajun Wu      Jun-Yan Zhu
Joshua B. Tenenbaum      Antonio Torralba      Russ Tedrake

MIT CSAIL


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.


Paper

Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, and Russ Tedrake
Propagation Networks for Model-Based Control Under Partial Observation
arXiv, [PDF] [BibTeX]


Video



Comparison with Interaction Networks



Related Work


Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Rezende, Koray Kavukcuoglu
Interaction Networks for Learning about Objects, Relations and Physics
NIPS 2016

Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia
Graph Networks as Learnable Physics Engines for Inference and Control
ICML 2018

Battaglia et al.
Relational inductive biases, deep learning, and graph networks
arXiv