機器人學的一個重要領域是控制器的優化。目前，機器人在這一優化過程中常被視為一個黑箱，這就是無導數優化方法如進化算法或強化學習無處不在的原因。當使用基于梯度的方法時，模型保持較小或者依賴于雅可比矩陣的有限差分近似。随着參數數量的增加，這種方法很快變得昂貴，例如在深度學習中。我們建議實作一個現代實體引擎，它可以區分控制參數。這個引擎是為中央處理器和圖形處理器實作的。首先，本文展示了這種引擎如何加快優化過程，即使是小問題。此外，它解釋了為什麼這是一個深度問學習的替代方法，用于在機器人學中使用深度學習。最後，我們認為這是機器人學深入學習的一大步，因為它為優化機器人開辟了新的可能性，包括硬體和軟體。
原文題目：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
原文位址：https://arxiv.org/abs/1611.01652
機器人學深度學習的微分實體引擎.pdf