Jiexin Zhang

About

Jiexin Zhang is a rising researcher at the forefront of artificial intelligence, specializing in the intersection of reinforcement learning and behavior tree (BT) architectures. Her work directly tackles one of AI’s most pressing challenges: the interpretability of autonomous agent policies. Zhang’s key contributions lie in developing methods to generate and optimize BTs—modular, visual control structures—using both reinforcement learning and evolution-inspired approaches. By making complex AI policies more transparent and comprehensible, her research bridges the gap between high-performance learning and human-understandable design, a critical step for deploying AI in robotics and computer games. Her 2023 papers, including “Interpretable Reinforcement Learning of Behavior Trees” and “Learning Behavior Trees by Evolution-Inspired Approaches,” have each garnered 3 citations, establishing a foundation for a new generation of explainable AI systems. Zhang’s work is particularly notable for addressing the practical challenge of manual BT construction, which is error-prone and requires expert domain knowledge. By automating this process, she is paving the way for more accessible and reliable autonomous agents, making her a promising voice in the quest for trustworthy AI.

Research Focus

Key Achievements

Top Papers

1. 1
   Interpretable Reinforcement Learning of Behavior Trees

   3 citations · 2023
2. 2
   Learning Behavior Trees by Evolution-Inspired Approaches

   3 citations · 2023

Key Collaborators

Contact & Links