Fawang Zhang
Papers
2
Total Citations
8
H-Index
2
About
Fawang Zhang is a rising researcher at the forefront of optimal control and reinforcement learning, whose work bridges the gap between data-driven learning and principled control theory. His primary research areas include inverse optimal control (IOC) and multi-style reinforcement learning, with a focus on making autonomous systems more adaptable and interpretable. In his highly cited 2024 paper, "Inverse Model Predictive Control," Zhang introduced a novel framework for learning optimal control cost functions from expert demonstrations, moving beyond traditional finite-horizon IOC to infer underlying goals and preferences from rollout trajectories—a contribution that has already garnered 6 citations and is shaping how robots learn from human behavior. His follow-up work, "Multi-Style Distributional Soft Actor-Critic," tackles the challenge of training a single unified policy capable of producing diverse control behaviors, eliminating the need for separate, customized policies for each style. Though early in his career, Zhang’s innovative approaches to unifying control styles and learning cost functions are poised to impact fields from autonomous driving to robotic manipulation, marking him as a promising voice in modern control and decision-making research.
Research Focus
Key Achievements
Top Papers
- 1
- 2