Variational Quantum Circuit-Based Reinforcement Learning for Dynamic Portfolio Optimization

2026-01-20

AI Summary

This study addresses the high-dimensional, non-stationary challenge of dynamic portfolio optimization by introducing variational quantum circuits (VQCs) into deep reinforcement learning for the first time. The authors propose quantum-enhanced versions of the Deep Deterministic Policy Gradient (DDPG) and Deep Q-Network (DQN) algorithms, employing VQCs as policy function approximators. Experimental results on real-world financial market data demonstrate that the proposed quantum agents achieve comparable or superior risk-adjusted returns relative to classical counterparts while utilizing significantly fewer trainable parameters. These findings substantiate the theoretical promise and practical competitiveness of quantum reinforcement learning in complex financial decision-making tasks.

Technology Category

• Machine Learning: Quantum Machine Learning
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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

Problem

• dynamic portfolio optimization
• reinforcement learning
• quantum computing
• financial markets
• decision-making

Innovation

• Variational Quantum Circuits
• Quantum Reinforcement Learning
• Dynamic Portfolio Optimization
• Deep Q-Network
• Deep Deterministic Policy Gradient