最优控制算子视角与神经自适应谱方法
Optimal Control Operator Perspective and a Neural Adaptive Spectral Method
AI总结:
本文提出一种实例-解控制算子视角,以一次性方式求解最优控制问题,并设计神经自适应谱方法(NASM)实现该算子,通过理论误差界和实验验证了其高效性与泛化能力。
摘要:
最优控制问题(OCPs)涉及为动态系统寻找一个控制函数,使得成本泛函得到优化。这一问题在学术界和工业界的物理系统中都处于核心地位。本文提出了一种新颖的实例-解控制算子视角,该视角以一次性方式求解OCPs,无需直接依赖动力学的显式表达式或迭代优化过程。该控制算子通过一种名为神经自适应谱方法(NASM)的新型神经算子架构实现,该方法是经典谱方法的推广。我们通过给出NASM对控制算子的逼近误差界,从理论上验证了该视角和架构。在合成环境和真实世界数据集上的实验验证了我们方法的有效性和效率,包括运行时间的大幅加速,以及分布内和分布外的高质量泛化。
英文摘要:
Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academia and industry. In this paper, we propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner without direct dependence on the explicit expression of dynamics or iterative optimization processes. The control operator is implemented by a new neural operator architecture named Neural Adaptive Spectral Method (NASM), a generalization of classical spectral methods. We theoretically validate the perspective and architecture by presenting the approximation error bounds of NASM for the control operator. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach, including substantial speedup in running time, and high-quality in- and out-of-distribution generalization.
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。