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.
翻译:我们展示了Myriad,这是在JAX中写成的用于在现实世界持续环境中学习和规划的试床。Myriad的主要贡献是三重。首先,Myriad为机械学习实践者提供了在典型的自动差异工作流程中应用轨迹优化技术的机会。第二,Myriad提出了许多现实世界最佳控制问题,从生物学到医学到工程,供机器学习界使用。在连续的空间和时间里,这些环境保留了经常被标准基准所抽取的真实世界系统的一些复杂性。因此,Myriard努力成为应用现代机器学习技术进行影响真实世界任务的垫脚石。最后,我们利用Myriad 仓库展示了一种新的学习和控制任务方法。经过全面端到端培训,我们的模型利用了一个隐含的规划模块,超越了正常的神经差异方程式,使同时学习和规划与复杂的环境动态相结合。