Junhao Zhu

About

Junhao Zhu is a researcher specializing in the intersection of deep reinforcement learning and quantitative finance, with a particular focus on algorithmic portfolio management. His work has made notable strides in adapting cutting-edge reinforcement learning techniques — originally developed for game-playing and robotics — to the complex, dynamic environment of financial markets. Zhu's most influential contribution, "Adversarial Deep Reinforcement Learning in Portfolio Management" (2018), has garnered 57 citations and stands as a landmark study implementing and comparing three state-of-the-art continuous reinforcement learning algorithms: Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO), and Policy Gradient (PG) within a portfolio management framework. This was complemented by his closely related paper, "Deep Reinforcement Learning in Portfolio Management" (2018, 23 citations), which laid the groundwork for applying DDPG and PPO to automated investment strategies. Together, these works have accumulated 80 citations, reflecting their meaningful impact on the growing field of AI-driven finance. Zhu's research is particularly valuable for students and practitioners seeking to understand how advanced machine learning methods can be rigorously adapted to solve real-world financial decision-making problems.

Research Focus

Key Achievements

Top Papers

1. 1
   Adversarial Deep Reinforcement Learning in Portfolio Management

   57 citations · 2018
2. 2
   Deep Reinforcement Learning in Portfolio Management

   23 citations · 2018

Key Collaborators

Contact & Links