Portfolio Management using Deep Reinforcement Learning

ArXiv ID: 2405.01604 “View on arXiv”

Authors: Unknown

Abstract

Algorithmic trading or Financial robots have been conquering the stock markets with their ability to fathom complex statistical trading strategies. But with the recent development of deep learning technologies, these strategies are becoming impotent. The DQN and A2C models have previously outperformed eminent humans in game-playing and robotics. In our work, we propose a reinforced portfolio manager offering assistance in the allocation of weights to assets. The environment proffers the manager the freedom to go long and even short on the assets. The weight allocation advisements are restricted to the choice of portfolio assets and tested empirically to knock benchmark indices. The manager performs financial transactions in a postulated liquid market without any transaction charges. This work provides the conclusion that the proposed portfolio manager with actions centered on weight allocations can surpass the risk-adjusted returns of conventional portfolio managers.

Keywords: Reinforcement learning, Portfolio optimization, Deep Q-Networks, Algorithmic trading, Risk-adjusted returns

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 3.0/10
• Quadrant: Lab Rats
• Why: The paper employs advanced DRL architectures (DQN, A2C, DDPG, LSTMs) and discusses MDP formulations, representing significant mathematical complexity. However, the empirical testing is described in a ‘postulated liquid market without transaction costs’ and lacks details on code, specific datasets, or statistical robustness, making it not backtest-ready.

  flowchart TD
    A["Research Goal:<br>Develop DRL Portfolio Manager<br>to outperform benchmarks"] --> B["Methodology:<br>Deep Reinforcement Learning<br>DQN & A2C Models"]
    B --> C["Data/Inputs:<br>Historical Market Data<br>Asset Prices & Volatility"]
    C --> D["Computational Process:<br>Environment Simulation<br>Weight Allocation & Short Selling"]
    D --> E["Training:<br>Learning Trading Policies<br>Optimization without Transaction Costs"]
    E --> F["Outcome:<br>Superior Risk-Adjusted Returns<br>vs. Conventional Managers"]
    F --> G["Conclusion:<br>DRL effective for Portfolio Optimization"]