Skip to yearly menu bar Skip to main content


End-to-End Differentiable Physics for Learning and Control

Filipe de Avila Belbute Peres · Kevin Smith · Kelsey Allen · Josh Tenenbaum · J. Zico Kolter

Room 210 #38

Keywords: [ Deep Learning ] [ Optimization ] [ Decision and Control ] [ Reinforcement Learning ] [ Model-Based RL ]


We present a differentiable physics engine that can be integrated as a module in deep neural networks for end-to-end learning. As a result, structured physics knowledge can be embedded into larger systems, allowing them, for example, to match observations by performing precise simulations, while achieves high sample efficiency. Specifically, in this paper we demonstrate how to perform backpropagation analytically through a physical simulator defined via a linear complementarity problem. Unlike traditional finite difference methods, such gradients can be computed analytically, which allows for greater flexibility of the engine. Through experiments in diverse domains, we highlight the system's ability to learn physical parameters from data, efficiently match and simulate observed visual behavior, and readily enable control via gradient-based planning methods. Code for the engine and experiments is included with the paper.

Live content is unavailable. Log in and register to view live content