arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.02202cs.LGcs.NEcs.RO
收藏

通过学习和进化的具身智能

Embodied Intelligence via Learning and Evolution

Department of Computer Science, Stanford University（斯坦福大学计算机科学系）；Department of Applied Physics, Stanford University（斯坦福大学应用物理系）；Wu-Tsai Neurosciences Institute, Stanford University（斯坦福大学吴蔡神经科学研究所）；Stanford Institute for Human-Centered Artificial Intelligence, Stanford University（斯坦福大学以人为本人工智能研究院）

Agrim Gupta, Silvio Savarese, Surya Ganguli, Li Fei-Fei

备注：
Video available at https://youtu.be/MMrIiNavkuY
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

复杂环境生态位中相互交织的学习和进化过程导致了形态形式的显着多样性。此外，动物智力的许多方面都深深地体现在这些进化的形态中。然而，环境的复杂性，进化形态学和智能控制的可学习性之间的关系的原则，仍然难以捉摸，部分原因是由于在进化和学习进行大规模的硅片实验的实质性挑战。我们介绍了深度进化强化学习（DERL）：一种新的计算框架，它可以进化不同的代理形态，学习具有挑战性的运动和操作任务，在复杂的环境中，只使用低层次的自我中心的感觉信息。利用DERL，我们展示了环境复杂性，形态智能和控制的可学习性之间的几种关系。首先，环境的复杂性促进了形态智能的进化，形态智能的进化可以通过形态学促进新任务的学习来量化。第二，进化迅速选择了学习速度更快的形态，从而使早期祖先在生命后期学到的行为能够在其后代的生命早期表达出来。在复杂环境中学习和进化的代理中，这一结果首次证明了长期存在的形态学鲍德温效应。第三，我们的实验为鲍德温效应和形态智能的出现提供了一个机械基础，通过形态的进化，形态在物理上更稳定，更节能，因此可以促进学习和控制。

英文摘要：

The intertwined processes of learning and evolution in complex environmental niches have resulted in a remarkable diversity of morphological forms. Moreover, many aspects of animal intelligence are deeply embodied in these evolved morphologies. However, the principles governing relations between environmental complexity, evolved morphology, and the learnability of intelligent control, remain elusive, partially due to the substantial challenge of performing large-scale in silico experiments on evolution and learning. We introduce Deep Evolutionary Reinforcement Learning (DERL): a novel computational framework which can evolve diverse agent morphologies to learn challenging locomotion and manipulation tasks in complex environments using only low level egocentric sensory information. Leveraging DERL we demonstrate several relations between environmental complexity, morphological intelligence and the learnability of control. First, environmental complexity fosters the evolution of morphological intelligence as quantified by the ability of a morphology to facilitate the learning of novel tasks. Second, evolution rapidly selects morphologies that learn faster, thereby enabling behaviors learned late in the lifetime of early ancestors to be expressed early in the lifetime of their descendants. In agents that learn and evolve in complex environments, this result constitutes the first demonstration of a long-conjectured morphological Baldwin effect. Third, our experiments suggest a mechanistic basis for both the Baldwin effect and the emergence of morphological intelligence through the evolution of morphologies that are more physically stable and energy efficient, and can therefore facilitate learning and control.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑