Corpus ID: 237513857

WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio Management

  title={WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio Management},
  author={Saeed Marzban and Erick Delage and Jonathan Yu-Meng Li and Jeremie Desgagne-Bouchard and Carl Dussault},
The problem of portfolio management represents an important and challenging class of dynamic decision making problems, where rebalancing decisions need to be made over time with the consideration of many factors such as investors’ preferences, trading environments, and market conditions. In this paper, we present a new portfolio policy network architecture for deep reinforcement learning (DRL) that can exploit more effectively cross-asset dependency information and achieve better performance… Expand


Relation-Aware Transformer for Portfolio Policy Learning
This paper proposes a novel Relation-aware Transformer (RAT) that is structurally innovated to capture both sequential patterns and asset correlations for portfolio selection and is able to make profitable portfolio decisions regarding each asset via a newly devised leverage operation. Expand
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
A novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. Expand
A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem
A financial-model-free Reinforcement Learning framework to provide a deep machine learning solution to the portfolio management problem, able to achieve at least 4-fold returns in 50 days. Expand
Adversarial Deep Reinforcement Learning in Portfolio Management
A so called Adversarial Training method is proposed and it can greatly improve the training efficiency and significantly promote average daily return and sharpe ratio in back test and results show that the agent based on Policy Gradient can outperform UCRP. Expand
Performance functions and reinforcement learning for trading systems and portfolios
We propose to train trading systems and portfolios by optimizing objective functions that directly measure trading and investment performance. Rather than basing a trading system on forecasts orExpand
An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown
An adaptive E(MDD) risk based RRL portfolio rebalancing decision system with a transaction cost and market condition stop-loss retraining mechanism is proposed, and it is shown that the proposed portfolio trading system responds to transaction cost effects better and outperforms hedge fund benchmarks consistently. Expand
Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning
It is shown that in certain settings, the available data can be dramatically increased through a form of multi-task learning, by exploiting an invariance property in the tasks, and a theoretical performance bound for the gain in sample efficiency under this setting is provided. Expand
Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach
  • Yan Li, Lingxiao Wang, +4 authors H. Zha
  • Computer Science
  • ArXiv
  • 2021
The meanfield proximal policy optimization (MF-PPO) algorithm is proposed, at the core of which is a permutationinvariant actor-critic neural architecture, and it is proved that MF- PPO attains the globally optimal policy at a sublinear rate of convergence. Expand
W ITHIN the last few years considerable progress has been made in three closely related areas-the theory of portfolio selection,1 the theory of the pricing of capital assets under conditions ofExpand
Transaction cost optimization for online portfolio selection
Empirical evaluations show that the proposed TCO framework may effectively handle reasonable transaction costs and improve existing strategies in the case of non-zero transaction costs. Expand