Myriad:连接轨迹优化和深度学习的真实测试平台
Myriad: a real-world testbed to bridge trajectory optimization and deep learning
摘要:
我们提出了Myriad,这是一个用JAX编写的测试平台,用于在现实世界的连续环境中进行学习和规划。Myriad的主要贡献有三个方面。首先,Myriad为机器学习从业者提供了轨迹优化技术,以应用于典型的自动微分工作流程。其次,Myriad提出了许多现实世界的最优控制问题,从生物学到医学再到工程学,供机器学习社区使用。这些环境在连续的空间和时间中制定,保留了一些现实世界系统的复杂性,通常被标准基准抽象掉。因此,Myriad致力于将现代机器学习技术应用于有影响力的现实任务。最后,我们使用Myriad存储库来展示一种用于学习和控制任务的新方法。我们的模型以完全端到端的方式进行训练,利用神经常微分方程的隐式规划模块,实现复杂环境动态的同时学习和规划。
英文摘要:
We present Myriad, a testbed written in JAX for learning and planning in real-world continuous environments. The primary contributions of Myriad are threefold. First, Myriad provides machine learning practitioners access to trajectory optimization techniques for application within a typical automatic differentiation workflow. Second, Myriad presents many real-world optimal control problems, ranging from biology to medicine to engineering, for use by the machine learning community. Formulated in continuous space and time, these environments retain some of the complexity of real-world systems often abstracted away by standard benchmarks. As such, Myriad strives to serve as a stepping stone towards application of modern machine learning techniques for impactful real-world tasks. Finally, we use the Myriad repository to showcase a novel approach for learning and control tasks. Trained in a fully end-to-end fashion, our model leverages an implicit planning module over neural ordinary differential equations, enabling simultaneous learning and planning with complex environment dynamics.
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。