MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management
Not on the map. Why?
Abstract (arXiv)
Deep reinforcement learning (DRL) has been applied in financial portfolio management to improve returns in changing market conditions. However, unlike most fields where DRL is widely used, the stock market is more volatile and dynamic as it is affected by several factors such as global events and investor sentiment. Therefore, it remains a challenge to construct a DRL-based portfolio management framework with strong return capability, stable training, and generalization ability. This study introduces a new framework utilizing the Memory Instance Gated Transformer (MIGT) for effective portfolio management. By incorporating a novel Gated Instance Attention module, which combines a transformer variant, instance normalization, and a Lite Gate Unit, our approach aims to maximize investment returns while ensuring the learning process's stability and reducing outlier impacts. Tested on the Dow Jones Industrial Average 30, our framework's performance is evaluated against fifteen other strategies using key financial metrics like the cumulative return and risk-return ratios (Sharpe, Sortino, and Omega ratios). The results highlight MIGT's advantage, showcasing at least a 9.75% improvement in cumulative returns and a minimum 2.36% increase in risk-return ratios over competing strategies, marking a significant advancement in DRL for portfolio management.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 97 references that are in the map. First posted on arXiv 11 Feb 2025.
Builds on
25 of 97 references.
References · 25
- 2017Attention Is All You Needcited by 59,932
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
- 2024Reinforcement learningcited by 236
- 2017A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problemcited by 123
- 2019Observational Overfitting in Reinforcement Learningcited by 90
- 2020FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Financecited by 86
- 2017Neural Optimizer Search with Reinforcement Learningcited by 82
13 more
- 2020Reinforcement Learning in Economics and Financecited by 57
- 2021FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Financecited by 57
- 2020Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction Statescited by 55
- 2016Cryptocurrency Portfolio Management with Deep Reinforcement Learningcited by 31
- 2019Radial-Based Undersampling for Imbalanced Data Classificationcited by 22
- 2020Fully Dynamic Inference with Deep Neural Networkscited by 19
- 2020Application of Deep Q-Network in Portfolio Managementcited by 11
- 2024Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimizationcited by 6
- 2021Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulationcited by 5
- 2021Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approachcited by 5
- 2019Deep Learning-Based Decoding of Constrained Sequence Codescited by 2
- 2025A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learningcited by 2
- 2021A Penalty Decomposition Algorithm with Greedy Improvement for Mean-Reverting Portfolios with Sparsity and Volatility Constraintscited by 1
Built on by
Not cited yet.