# Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket

arXiv: https://arxiv.org/abs/2105.08664 · HTML: https://mlsanity.com/paper/2105.08664/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 77 references that are in the map.
- First posted on arXiv 6 May 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Deep Convolutional Networks on Graph-Structured Data](https://mlsanity.com/paper/1506.05163/) (2015)
- [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://mlsanity.com/paper/1706.10059/) (2017)
- [Vertex-Frequency Analysis on Graphs](https://mlsanity.com/paper/1307.5708/) (2013)
- [Relational Autoencoder for Feature Extraction](https://mlsanity.com/paper/1802.03145/) (2018)
- [Teaching Compositionality to CNNs](https://mlsanity.com/paper/1706.04313/) (2017)
- [Impact of Data Normalization on Deep Neural Network for Time Series Forecasting](https://mlsanity.com/paper/1812.05519/) (2018)

## Built on by (most cited first, 13 of 13)

- [FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting](https://mlsanity.com/paper/2502.18834/) (2025)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions](https://mlsanity.com/paper/2401.09769/) (2024)
- [The Evolution of Reinforcement Learning in Quantitative Finance: A Survey](https://mlsanity.com/paper/2408.10932/) (2024)
- [LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU](https://mlsanity.com/paper/2409.08282/) (2024)
- [MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU](https://mlsanity.com/paper/2410.20679/) (2024)
- [Beyond Fixed Patches: Enhancing GPTs for Financial Prediction with Adaptive Segmentation and Learnable Wavelets](https://mlsanity.com/paper/2505.02880/) (2025)
- [GraphGen+: Advancing Distributed Subgraph Generation and Graph Learning On Industrial Graphs](https://mlsanity.com/paper/2503.06212/) (2025)
- [Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning](https://mlsanity.com/paper/2508.03910/) (2025)
- [Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization](https://mlsanity.com/paper/2511.17963/) (2025)
- [Incorporating rank-free coupling and external field via an incoherent modulated spatial photonic Ising machine](https://mlsanity.com/paper/2512.21587/) (2025)
- [Fluid-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.14559/) (2026)
- [Regime-Adaptive Continual Learning for Portfolio Management](https://mlsanity.com/paper/2606.00143/) (2026)

## Abstract (arXiv)

Portfolio management aims at maximizing the return on investment while minimizing risk by continuously reallocating the assets forming the portfolio. These assets are not independent but correlated during a short time period. A graph convolutional reinforcement learning framework called DeepPocket is proposed whose objective is to exploit the time-varying interrelations between financial instruments. These interrelations are represented by a graph whose nodes correspond to the financial instruments while the edges correspond to a pair-wise correlation function in between assets. DeepPocket consists of a restricted, stacked autoencoder for feature extraction, a convolutional network to collect underlying local information shared among financial instruments, and an actor-critic reinforcement learning agent. The actor-critic structure contains two convolutional networks in which the actor learns and enforces an investment policy which is, in turn, evaluated by the critic in order to determine the best course of action by constantly reallocating the various portfolio assets to optimize the expected return on investment. The agent is initially trained offline with online stochastic batching on historical data. As new data become available, it is trained online with a passive concept drift approach to handle unexpected changes in their distributions. DeepPocket is evaluated against five real-life datasets over three distinct investment periods, including during the Covid-19 crisis, and clearly outperformed market indexes.