Dynamic Portfolio Optimization via Augmented DDPG with Quantum Price Levels-Based Trading Strategy

TL;DR

This work tackles Dynamic Portfolio Optimization under noisy markets by introducing an Augmented DDPG framework with a shared Actor-Critic encoder to boost training efficiency, paired with a Quantum Price Levels (QPLs)-driven risk-control module via a Policy Gradient agent. The QPLs, derived from Quantum Finance Theory, provide a volatility-aware mechanism that guides intraday risk management, while the Gini bonus in the reward promotes diversification. Empirical results on five-asset Forex data show superior ARR and stable Sharpe ratios with lower MDD and reduced sample complexity compared to baselines. The approach highlights the practical potential of combining quantum-inspired volatility indicators with multi-agent DRL for robust, scalable DPO in finance, with future work targeting NLP-enhanced information streams.

Abstract

With the development of deep learning, Dynamic Portfolio Optimization (DPO) problem has received a lot of attention in recent years, not only in the field of finance but also in the field of deep learning. Some advanced research in recent years has proposed the application of Deep Reinforcement Learning (DRL) to the DPO problem, which demonstrated to be more advantageous than supervised learning in solving the DPO problem. However, there are still certain unsolved issues: 1) DRL algorithms usually have the problems of slow learning speed and high sample complexity, which is especially problematic when dealing with complex financial data. 2) researchers use DRL simply for the purpose of obtaining high returns, but pay little attention to the problem of risk control and trading strategy, which will affect the stability of model returns. In order to address these issues, in this study we revamped the intrinsic structure of the model based on the Deep Deterministic Policy Gradient (DDPG) and proposed the Augmented DDPG model. Besides, we also proposed an innovative risk control strategy based on Quantum Price Levels (QPLs) derived from Quantum Finance Theory (QFT). Our experimental results revealed that our model has better profitability as well as risk control ability with less sample complexity in the DPO problem compared to the baseline models.

Figures (5)

• Figure 2: System Architecture
• Figure 3: Cumulative Returns of Different Models
• Figure 4: Sharpe Ratio of Different Models
• Figure 5: Comparison of Training Efficiency
• Figure 6: Cumulative Returns with Different Gini Bonus Coefficients