一种用于经济学中有限时域随机控制问题的机器学习算法
A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics
AI总结:
本文提出一种基于深度神经网络表示最优策略函数的机器学习算法,可求解高维有限时域时不齐次随机控制问题,具有单调收敛性且不依赖Bellman方程,并在多类经济模型中验证了有效性。
摘要:
我们提出一种用于求解有限时域随机控制问题的机器学习算法,该算法基于最优策略函数的深度神经网络表示。该算法具有三个特点:(1)它能够求解高维(例如超过100维)且有限时域的时不齐次随机控制问题。(2)它在每次迭代中都具有性能改进的单调性,从而带来良好的收敛性质。(3)它不依赖于Bellman方程。为证明该算法的效率,我们将其应用于求解多种有限时域时不齐次问题,包括随机波动率模型下的递归效用优化、多部门随机增长,以及在气候与经济动态随机整合模型下、具有八维状态向量和600个时间周期的最优控制问题。
英文摘要:
We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve high-dimensional (e.g., over 100 dimensions) and finite-horizon time-inhomogeneous stochastic control problems. (2) It has a monotonicity of performance improvement in each iteration, leading to good convergence properties. (3) It does not rely on the Bellman equation. To demonstrate the efficiency of the algorithm, it is applied to solve various finite-horizon time-inhomogeneous problems including recursive utility optimization under a stochastic volatility model, a multi-sector stochastic growth, and optimal control under a dynamic stochastic integration of climate and economy model with eight-dimensional state vectors and 600 time periods.
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。