Papers
2
Total Citations
25
H-Index
2
About
Chenyang Miao is a researcher advancing the frontiers of intelligent control and multi-agent systems through reinforcement learning (RL). His primary research areas include multi-agent deep reinforcement learning, robot manipulation, and the integration of dynamic movement primitives (DMPs) with RL for efficient policy learning. Miao’s most influential work, "Effective Multi-Agent Deep Reinforcement Learning Control With Relative Entropy Regularization" (2024, 19 citations), introduces the Multi-Agent Continuous Dynamic Policy Gradient (MACDPP) algorithm, which addresses the challenge of rapidly exploring optimal control policies in unknown environments—a critical step for scalable autonomous systems. In his second highly cited paper (6 citations), Miao bridges RL with DMPs to enable efficient robot manipulation, allowing robots to autonomously learn smooth, adaptable trajectories without extensive manual tuning. These contributions demonstrate his ability to solve real-world control problems by combining theoretical rigor with practical algorithm design. With a growing citation footprint, Miao’s work is shaping the next generation of autonomous agents and robotic systems, offering students and researchers a clear pathway from foundational RL theory to deployable, intelligent control.
Research Focus
Key Achievements
Top Papers
- 1
- 2