Kangkang Jiang

About

Kangkang Jiang is a researcher at the forefront of applying deep reinforcement learning to quantitative finance, with a particular focus on autonomous portfolio management. Their work bridges the gap between cutting-edge artificial intelligence techniques and real-world financial decision-making, demonstrating that algorithms originally designed for game-playing and robotic control can be successfully adapted to dynamic investment strategies. Jiang's most influential contribution, "Adversarial Deep Reinforcement Learning in Portfolio Management" (2018, 57 citations), introduced an adversarial training framework incorporating state-of-the-art continuous reinforcement learning algorithms — including Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO), and Policy Gradient (PG) — to optimize portfolio allocation. This was complemented by the closely related "Deep Reinforcement Learning in Portfolio Management" (2018, 23 citations), which laid foundational groundwork for applying DDPG and PPO to financial markets. Together, these papers have accumulated 80 citations, establishing Jiang as a notable contributor to the emerging field of AI-driven finance. Their research is particularly valuable for students and practitioners interested in algorithmic trading, demonstrating how reinforcement learning can navigate the complex, stochastic nature of financial markets with promising results.

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