Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning

Value-function (VF) approximation is a central problem in Reinforcement Learning (RL). Classical non-parametric VF estimation suffers from the curse of dimensionality. As a result, parsimonious parametric models have been adopted to approximate VFs in high-dimensional spaces, with most efforts being focused on linear and neural-network-based approaches.

价值函数（Value-function, VF）近似是强化学习（Reinforcement Learning, RL）中的核心问题。经典非参数VF估计存在维数灾难问题。为此，学界已采用简约参数化模型在高维空间中近似价值函数，目前绝大多数相关研究聚焦于线性方法与基于神经网络的方法。