arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.04037math.OCmath.PR
收藏

一种用于非马尔可夫控制问题的策略迭代算法

A policy iteration algorithm for non-Markovian control problems

Dylan Possamaï, Ludovic Tangpi

AI总结:

针对连续时间随机控制问题,提出基于线性二次逼近的新型策略迭代算法,证明值与控制具有指数收敛速度,并首次覆盖多维波动率控制。

摘要:

本文提出了一种新的策略迭代算法,用于计算连续时间随机控制问题的值函数和最优控制。该算法依赖于利用线性二次控制问题进行逐次逼近,这些线性二次控制问题均可显式求解,并且在马尔可夫情形下只需求解递归线性偏微分方程。尽管我们的过程通常无法像标准算法那样产生非递减序列,但可以使其任意接近单调。更重要的是,我们通过比经典情形显著更简单的纯概率论证,恢复了值和控制的标准指数收敛速度。我们的证明还适用于非马尔可夫动力学以及波动率控制,使我们在后一种情形下首次获得了多维状态过程的收敛结果。

英文摘要:

In this paper, we propose a new policy iteration algorithm to compute the value function and the optimal controls of continuous time stochastic control problems. The algorithm relies on successive approximations using linear-quadratic control problems which can all be solved explicitly, and only require to solve recursively linear PDEs in the Markovian case. Though our procedure fails in general to produce a non-decreasing sequence like the standard algorithm, it can be made arbitrarily close to being monotone. More importantly, we recover the standard exponential speed of convergence for both the value and the controls, through purely probabilistic arguments which are significantly simpler than in the classical case. Our proof also accommodates non-Markovian dynamics as well as volatility control, allowing us to obtain the first convergence results in the latter case for a state process in multi-dimensions.

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。

↑