Tonghan Wang
Papers
1
Total Citations
3
H-Index
1
About
Tonghan Wang is a researcher advancing the frontiers of reinforcement learning (RL) and robotics, with a focus on scalable, biologically inspired control systems. His key research areas include modular reinforcement learning, multi-agent systems, and low-rank control architectures. Wang’s major contribution is the development of "Low-Rank Modular Reinforcement Learning via Muscle Synergy," a 2022 work that addresses a critical bottleneck in modular RL: the exponential growth in complexity with increased degrees of freedom in multi-joint robots. By drawing inspiration from biological muscle synergies, he introduced a low-rank decomposition method that enables efficient, decentralized policy learning for each actuator, dramatically reducing computational overhead while maintaining robust control across morphologically diverse agents. This work, already garnering 3 citations, has opened new pathways for scalable robot control. Wang’s research is notable for bridging neuroscience and machine learning, offering a principled approach to managing high-dimensional action spaces. His achievements position him as a rising voice in the quest for more adaptive, efficient autonomous systems, with potential applications ranging from prosthetics to industrial robotics.
Research Focus
Key Achievements
Top Papers
- 1Low-Rank Modular Reinforcement Learning via Muscle Synergy3 citations · 2022