arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09280math.OC
收藏

基于值梯度的最优控制问题形式化及机器学习算法

Value-Gradient based Formulation of Optimal Control Problem and Machine Learning Algorithm

Alain Bensoussan, Jiayue Han, Sheung Chi Phillip Yam, Xiang Zhou

摘要:

最优控制问题的求解一般是通过哈密尔顿-雅可比方程(HJE)求出值函数,然后取哈密尔顿算子的极小值来获得控制。在这项工作中,而不是专注于价值函数,我们提出了一个新的配方的价值函数(价值梯度)的梯度作为一个解耦的偏微分方程系统的背景下,连续时间确定性折扣最优控制问题。我们开发了一个有效的迭代计划,该方程组方程并行利用的属性,他们共享相同的特征曲线的HJE的值函数。在理论部分,我们证明了对于权函数中的适当指数$α$,该迭代格式在$L_α^2$意义下线性收敛。对于数值方法,我们将特征线方法与机器学习技术相结合。具体来说,我们在每次策略迭代时从初始状态的集合生成多条特征曲线,并同时计算每条曲线上的值函数及其梯度作为标记数据。然后应用监督机器学习来最小化值函数及其梯度的加权平方损失。实验结果表明,该方法不仅显著提高了估计精度,而且提高了估计的效率和鲁棒性,特别是在特征数据量较少或训练步骤较少的情况下。

英文摘要:

Optimal control problem is typically solved by first finding the value function through Hamilton-Jacobi equation (HJE) and then taking the minimizer of the Hamiltonian to obtain the control. In this work, instead of focusing on the value function, we propose a new formulation for the gradient of the value function (value-gradient) as a decoupled system of partial differential equations in the context of continuous-time deterministic discounted optimal control problem. We develop an efficient iterative scheme for this system of equations in parallel by utilizing the properties that they share the same characteristic curves as the HJE for the value function. For the theoretical part, we prove that this iterative scheme converges linearly in $L_α^2$ sense for some suitable exponent $α$ in a weight function. For the numerical method, we combine characteristic line method with machine learning techniques. Specifically, we generate multiple characteristic curves at each policy iteration from an ensemble of initial states, and compute both the value function and its gradient simultaneously on each curve as the labelled data. Then supervised machine learning is applied to minimize the weighted squared loss for both the value function and its gradients. Experimental results demonstrate that this new method not only significantly increases the accuracy but also improves the efficiency and robustness of the numerical estimates, particularly with less amount of characteristics data or fewer training steps.

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。

↑