arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.02272eess.SYcs.SY
收藏

离散时间最大似然神经分布引导

Discrete-Time Maximum Likelihood Neural Distribution Steering

George Rapakoulias, Panagiotis Tsiotras

AI总结:

本文提出一种基于神经网络的离散时间系统分布引导方法,将问题转化为正则化最大似然优化,并通过数值实验验证其在非高斯边界分布和非线性动态等复杂场景下的有效性。

摘要:

本文研究在有限时间内将离散时间动力系统的分布从初始分布引导至目标分布的问题。该问题的表述是完全非线性的,允许使用由神经网络参数化的一般控制策略。尽管在连续时间背景下已有类似的解决方案被探索过,但将这些技术扩展到具有离散动态的系统并非易事。所提出的算法归结为一个正则化最大似然优化问题,并利用机器学习技术进行求解。在给出算法之后,我们提供了若干数值示例来说明所提方法的能力。我们首先从一个可通过半定规划求解的简单问题入手,将其作为所提方法的基准。随后,我们将该框架应用于现有技术无法解决的更一般的问题,例如具有非高斯边界分布和非线性动态的问题。

英文摘要:

This paper studies the problem of steering the distribution of a discrete-time dynamical system from an initial distribution to a target distribution in finite time. The formulation is fully nonlinear, allowing the use of general control policies, parametrized by neural networks. Although similar solutions have been explored in the continuous-time context, extending these techniques to systems with discrete dynamics is not trivial. The proposed algorithm results in a regularized maximum likelihood optimization problem, which is solved using machine learning techniques. After presenting the algorithm, we provide several numerical examples that illustrate the capabilities of the proposed method. We start from a simple problem that admits a solution through semidefinite programming, serving as a benchmark for the proposed approach. Then, we employ the framework in more general problems that cannot be solved using existing techniques, such as problems with non-Gaussian boundary distributions and non-linear 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。

↑