当前位置: X-MOL 学术Operations Research Letters › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
WaveCorr: Deep reinforcement learning with permutation invariant convolutional policy networks for portfolio management
Operations Research Letters ( IF 1.1 ) Pub Date : 2023-11-04 , DOI: 10.1016/j.orl.2023.10.011
Saeed Marzban , Erick Delage , Jonathan Yumeng Li , Jeremie Desgagne-Bouchard , Carl Dussault

We present a new portfolio policy convolutional neural network architecture, WaveCorr, for deep reinforcement learning applied to portfolio optimization. WaveCorr is the first to treat asset correlation while preserving “asset invariance property”, a new permutation invariance property that significantly increases the stability of performance in problems where input indexing is done arbitrarily. A general theory is also derived for verifying this property in other fields of application. Our experiments show that WaveCorr consistently outperforms other state-of-the-art convolutional architectures.



中文翻译:

WaveCorr:用于投资组合管理的具有排列不变卷积策略网络的深度强化学习

我们提出了一种新的投资组合策略卷积神经网络架构 WaveCorr,用于将深度强化学习应用于投资组合优化。WaveCorr 是第一个在保留“资产不变性”的同时处理资产相关性的方法,这是一种新的排列不变性,可以显着提高任意输入索引问题中的性能稳定性。还导出了一个通用理论,用于在其他应用领域验证该特性。我们的实验表明,WaveCorr 始终优于其他最先进的卷积架构。

更新日期:2023-11-04
down
wechat
bug