Zhuoran Yang
Papers
7
Total Citations
1,368
H-Index
7
About
Zhuoran Yang is a leading researcher in multi-agent reinforcement learning (MARL), a field at the intersection of machine learning and control systems. His major contributions include providing comprehensive theoretical frameworks and algorithms for MARL, particularly in decentralized settings where agents must coordinate through networked communication. His most influential work, the 2021 survey "Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms," has accumulated over 1,100 citations, establishing itself as a foundational reference in the field. Yang has also advanced practical MARL through innovative optimization methods, such as double averaging primal-dual approaches and homotopy stochastic primal-dual optimization for temporal-difference learning, enabling faster and more stable policy evaluation in multi-agent systems. His research addresses critical challenges in decentralized applications, including sensor networks, swarm robotics, and power grids. Additionally, Yang contributed to scalable deep RL infrastructure with the ElegantRL-Podracer library, designed for cloud-native environments. His work bridges rigorous theory with practical deployment, making him a key figure in the ongoing evolution of multi-agent systems and reinforcement learning.
Research Focus
Key Achievements
Top Papers
- 1Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms1,121 citations · 2021
- 2
- 3
- 4
- 5
- 6
- 7