A Differentiable Physics Engine for Deep Learning
A Differentiable Physics Engine for Deep Learning
复制标题
用于深度学习的可微分物理引擎
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Jonas Degrave
中科院分区：
文献类型：
--
作者：
Jonas Degrave
机器人技术中最重要的领域之一是控制器的优化。目前，机器人在这个优化过程中被视为黑箱，这就是为什么进化算法或强化学习等无导数优化方法无处不在的原因。我们提出了一个现代物理引擎的实现，它具有区分控制参数的能力。这已经在CPU和GPU上实现。我们展示了这是如何加快优化过程的，即使是小问题，以及为什么它会扩展到更大的问题。我们解释了为什么这是深度Q学习的替代方法，用于机器人技术中的深度学习。最后，我们认为这是机器人深度学习的一大步，因为它为优化机器人的硬件和软件开辟了新的可能性。
One of the most important fields in robotics is the optimization of controllers. Currently, robots are 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. We propose an implementation of a modern physics engine, which has the ability to differentiate control parameters. This has been implemented on both CPU and GPU. We show how this speeds up the optimization process, even for small problems, and why it will scale to bigger problems. We explain why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Lastly, 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.