机器人学的一个重要领域是控制器的优化。目前，机器人在这一优化过程中常被视为一个黑箱，这就是无导数优化方法如进化算法或强化学习无处不在的原因。当使用基于梯度的方法时，模型保持较小或者依赖于雅可比矩阵的有限差分近似。随着参数数量的增加，这种方法很快变得昂贵，例如在深度学习中。我们建议实现一个现代物理引擎，它可以区分控制参数。这个引擎是为中央处理器和图形处理器实现的。首先，本文展示了这种引擎如何加快优化过程，即使是小问题。此外，它解释了为什么这是一个深度问学习的替代方法，用于在机器人学中使用深度学习。最后，我们认为这是机器人学深入学习的一大步，因为它为优化机器人开辟了新的可能性，包括硬件和软件。
原文题目：A Differentiable Physics Engine for Deep Learning in Robotics
原文：An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms 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 the 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 software.
原文作者：Jonas Degrave, Michiel Hermans, Joni Dambre, Francis wyffels
原文地址：https://arxiv.org/abs/1611.01652
机器人学深度学习的微分物理引擎.pdf