arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11485math.OC
收藏

逆随机最优控制

Inverse stochastic optimal controls

Yumiharu Nakano

摘要:

研究了一类性能指标中含有控制过程二次惩罚项的一般扩散随机最优控制的反问题。在系统动力学、代价函数和最优控制过程的温和条件下,利用随机最大值原理证明了我们的逆问题是适定的。然后,利用适定性,将反问题归结为一个包含值函数的随机变量的期望的求根问题,该问题有唯一解。在此基础上,我们提出了一种用观测到的最优控制过程和相应的状态过程的算术平均值代替上述期望值的数值方法。Hamilton-Jacobi-Bellman方程数值分析的最新进展使该方法可用于多维情形。特别地,在Hamilton-Jacobi-Bellman方程的基于核的配置法的帮助下,我们的反问题方法即使在没有显式值函数的情况下也能很好地工作.数值实验表明,数值方法能够以较高的精度恢复未知的罚参数。

英文摘要:

We study an inverse problem of the stochastic optimal control of general diffusions with performance index having the quadratic penalty term of the control process. Under mild conditions on the system dynamics, the cost functions, and the optimal control process, we show that our inverse problem is well-posed using a stochastic maximum principle. Then, with the well-posedness, we reduce the inverse problem to some root finding problem of the expectation of a random variable involved with the value function, which has a unique solution. Based on this result, we propose a numerical method for our inverse problem by replacing the expectation above with arithmetic mean of observed optimal control processes and the corresponding state processes. The recent progress of numerical analyses of Hamilton-Jacobi-Bellman equations enables the proposed method to be implementable for multi-dimensional cases. In particular, with the help of the kernel-based collocation method for Hamilton-Jacobi-Bellman equations, our method for the inverse problems still works well even when an explicit form of the value function is unavailable. Several numerical experiments show that the numerical method recovers the unknown penalty parameter with high accuracy.

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。

↑