arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.09736cs.LGcs.AI
收藏

强化学习中的张量与矩阵低秩值函数逼近

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

King Juan Carlos University(胡安·卡洛斯国王大学);Rensselaer Polytechnic Institute(伦斯勒理工学院)

Sergio Rozada, Santiago Paternain, Antonio G. Marques

AI总结:

本文提出用随机低秩算法在线无模型地估计值函数矩阵,并引入张量表示与PARAFAC分解设计张量低秩算法,以缓解维度灾难,在标准RL环境中验证了性能。

摘要:

值函数(VF)逼近是强化学习(RL)中的一个核心问题。经典的非参数化VF估计存在维度灾难问题。因此,在高维空间中,人们采用简约的参数化模型来逼近VF,其中大部分工作集中于线性和基于神经网络的方法。与此不同,本文提出了一种简约的非参数化方法,我们使用随机低秩算法以在线且无模型的方式估计VF矩阵。此外,由于VF往往是多维的,我们建议将经典的VF矩阵表示替换为张量(多维数组)表示,然后使用PARAFAC分解来设计一种在线无模型的张量低秩算法。我们提出了算法的不同版本,分析了它们的复杂度,并使用标准化的RL环境对其性能进行了数值评估。

英文摘要:

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. Differently, this paper puts forth a a parsimonious non-parametric approach, where we use stochastic low-rank algorithms to estimate the VF matrix in an online and model-free fashion. Furthermore, as VFs tend to be multi-dimensional, we propose replacing the classical VF matrix representation with a tensor (multi-way array) representation and, then, use the PARAFAC decomposition to design an online model-free tensor low-rank algorithm. Different versions of the algorithms are proposed, their complexity is analyzed, and their performance is assessed numerically using standardized RL environments.

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。

↑