MAC: A Multi-Agent Reinforcement Learning Framework with Correctable Strategies for Portfolio Management

Portfolio Management (PM) is a broad investment strategy aimed at risk mitigation through diversified financial product investments. Acknowledging the significance of dynamic adjustments after establishing a portfolio to enhance stability and returns, we propose employing Reinforcement Learning (RL) to address dynamic decision-making challenges. However, traditional RL methods often struggle to adapt to significant market volatility, primarily focusing on adjusting existing asset weights. Unlike traditional RL methods, our proposed Multi-Agent Reinforcement Learning Correctable Strategy (MAC) detects and replaces potentially harmful assets with familiar alternatives, ensuring a more resilient response to market crises. Utilizing the Multi-Agent Reinforcement Learning (MARL) model, MAC empowers individual agents to maximize portfolio returns and minimize risk separately. During training, MAC strategically replaces assets to simulate market changes, allowing agents to learn risk identification through uncertainty estima-tion. During testing, MAC dynamically detects potentially harmful assets and replaces them with more confident alternatives, enhancing portfolio stability. Experiments con-ducted on a real-world US Exchange-Traded Fund (ETF) market dataset demonstrate MAC’s superiority over standard RL-based PM methods and other baselines, underscor-ing its practical efficacy for real-world applications.

Recommended citation: Kuang-Da Wang*, Pei-Xuan Li*, Hsun-Ping Hsieh, Wen-Chih Peng. MAC: A Multi-Agent Reinforcement Learning Framework with Correctable Strategies for Portfolio Management. IEEE International Conference on Knowledge Innovation and Invention (ICKII) 2025 (Best paper award, * Equal contribution)
Download Paper | Download Slides