We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains-namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance.
We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains-namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance.
Financial market prediction and optimal trading strategy development remain challenging due to market complexity and volatility. Our research in quantum finance and reinforcement learning for decision-making demonstrates the approach of quantum-classical hybrid algorithms to tackling real-world finan-cial challenges. In this respect, we corroborate the concept with rigorous backtesting and validate the framework's performance under realistic market conditions, by including fixed transaction cost per trade. This paper introduces a Quantum Attention Deep Q-Network (QADQN) approach to address these challenges through quantum-enhanced reinforcement learning. Our QADQN architecture uses a variational quantum circuit inside a traditional deep Q-learning framework to take advantage of possible quantum advantages in decision-making. We gauge the QADQN agent's performance on historical data from major market indices, including the S&P 500. We evaluate the agent's learning process by examining its reward accumulation and the effectiveness of its experience replay mechanism. Our empirical results demonstrate the QADQN's superior performance, achieving better risk-adjusted returns with Sortino ratios of 1.28 and 1.19 for non-overlapping and overlapping test periods respectively, indicating effective downside risk management.
This Paper shows information about the High Speed Stock Trading, In todays era the normal computers are struggling to identify and find the complex market patterns and strategies. So in order to solve this issue we built a new system that is a combination of quantum computing and classical computing in which Reinforcement Learning (a way for computers to learn with trial and error) is used with Quantum Machine Learning to make smarter trading decisions and strategies. Specially, we have used a quantum model (called a Variational Quantum classifier) as a part of Deep Q Network agent to help the system learning better trading strategies. Our goal is to use the superior representational power of quantum feature spaces for financial decision making. The hybrid agent was trained in a high-fidelity simulation environment that includes realistic market frictions and a risk-adjusted reward function. Backtesting results on unseen data indicate that the hybrid agent consistently performs better than its traditional counterpart. It achieves a total return of 21.2%, which is higher than the 18.5% return from the classical model. Additionally, risk-adjusted performance has clearly improved. The hybrid agent’s Sortino Ratio is 32.6% higher and its Sharpe Ratio is 26.4% higher. Its maximum drawdown is also lower. These findings demonstrate that quantum models are able to detect minute market relationships that conventional approaches might miss. As a result, trading tactics become more reliable and successful. This research marks a substantial breakthrough in the application of quantum technologies to challenging computational finance problems.
In the era of Noisy Intermediate-Scale Quantum devices, Variational Quantum Circuits in Quantum Machine Learning are gaining attention, advancing towards practical quantum computing applications on NISQ devices. Reinforcement Learning (RL), known for its humanlike, trial-and-error learning, excels in adapting to changing financial environments. In particular, classical algorithms such as Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) show promise, while emerging quantum neural networks offer potential for improved function approximation, better generalization capabilities and reduced parameters. In light of these advancements, we introduce a quantum-enhanced version of the DDPG agent (QDDPG), aiming to leverage these quantum capabilities for more efficient financial decisionmaking processes. The quantum part of the model utilizes a parameterized quantum policy, which consists of a sequential reuploading variational circuit with trainable input scaling parameters. Our objective is to explore the practicality and potential benefits of QRL in finance, aiming to realize viable quantum computing applications on NISQ devices. The QDDPG model surpasses traditional analytic strategies in portfolio allocation, achieving higher returns with fewer parameters and a favourable Sharpe ratio. In a simple configuration using a RAW-parameterized quantum policy, the model achieves an average Sharpe ratio of 1.20 across 15 trained agents, compared to 0.96 for the minimum-variance strategy and 0.81 for the buy-and-hold baseline. Furthermore we investigate the impact of quantum noise, a significant challenge for NISQ devices. We analyze various types of noise, such as general depolarization, amplitude damping, phase damping, measurement noise, and shot noise, which uniquely affect quantum computations. Our study quantifies how these noise types influence the performance, reliability, and robustness of the QRL model. We study new techniques to harness quantum noise as hyperparameter to control the exploration-exploitation balance of the agent, using noise as regularization method and to stabilize the training of the agents. This comprehensive analysis aims to not only highlight the challenges posed by quantum noise but also to explore innovative methods to mitigate these effects and enhance the applicability of quantum algorithms in real-world applications.
Financial trading environments are characterized by high volatility, numerous macroeconomic signals, and dynamically shifting market regimes, where traditional reinforcement learning methods often fail to deliver breakthrough performance. In this study, we design a reinforcement learning framework tailored for financial systems by integrating quantum circuits. We compare (1) the performance of classical A3C versus quantum A3C algorithms, and (2) the impact of incorporating LSTM-based predictions of the following week's economic trends on learning outcomes. The experimental framework adopts a custom Gymnasium-compatible trading environment, simulating discrete trading actions and evaluating rewards based on portfolio feedback. Experimental results show that quantum models—especially when combined with predictive signals—demonstrate superior performance and stability under noisy financial conditions, even with shallow quantum circuit depth.
The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over around 5 years with 0.92\% max drawdown, outperforming several currency ETFs. We detail state design (QLSTM features and indicators), reward function for trend-following/risk control, and multi-core training. Results show hybrid models yield competitive FX trading performance. Implications include QLSTM's effectiveness for small-profit trades with tight risk and future enhancements. Key hyperparameters: QLSTM sequence length$=4,QA3Cworkers=$8. Limitations: classical quantum simulation and simplified strategy. \footnote{The views expressed in this article are those of the authors and do not represent the views of Wells Fargo. This article is for informational purposes only. Nothing contained in this article should be construed as investment advice. Wells Fargo makes no express or implied warranties and expressly disclaims all legal, tax, and accounting implications related to this article.
This paper presents a Quantum Reinforcement Learning (QRL) solution to the dynamic portfolio optimization problem based on Variational Quantum Circuits. The implemented QRL approaches are quantum analogues of the classical neural-network-based Deep Deterministic Policy Gradient and Deep Q-Network algorithms. Through an empirical evaluation on real-world financial data, we show that our quantum agents achieve risk-adjusted performance comparable to, and in some cases exceeding, that of classical Deep RL models with several orders of magnitude more parameters. However, while quantum circuit execution is inherently fast at the hardware level, practical deployment on cloud-based quantum systems introduces substantial latency, making end-to-end runtime currently dominated by infrastructural overhead and limiting practical applicability. Taken together, our results suggest that QRL is theoretically competitive with state-of-the-art classical reinforcement learning and may become practically advantageous as deployment overheads diminish. This positions QRL as a promising paradigm for dynamic decision-making in complex, high-dimensional, and non-stationary environments such as financial markets. The complete codebase is released as open source at: https://github.com/VincentGurgul/qrl-dpo-public