"A Differentiable Physics Engine for Deep Learning in Robotics"

Autor(en): Jonas Degrave, Michiel Hermans, Joni Dambre, Francis wyffels

One of the most important fields in robotics is the optimization of controllers. Cur-
rently, robots are often treated as a black box in this optimization process, which
is the reason why derivative-free optimization methods such as evolutionary algo-
rithms or reinforcement learning are omnipresent. When gradient-based methods
are used, models are kept small or rely on finite difference approximations for
the Jacobian. This method quickly grows expensive with increasing numbers of
parameters, such as found in deep learning. We propose an implementation of a
modern physics engine, which can differentiate control parameters. This engine
is implemented for both CPU and GPU. Firstly, this paper shows how such an
engine speeds up the optimization process, even for small problems. Furthermore,
it explains why this is an alternative approach to deep Q-learning, for using deep
learning in robotics. Finally, we argue that this is a big step for deep learning in
robotics, as it opens up new possibilities to optimize robots, both in hardware and

Link: https://openreview.net/pdf?id=SyEiHNKxx

last updated 31.03.2023