Tianhao Chen
Papers
1
Total Citations
5
H-Index
1
About
Tianhao Chen is a researcher advancing the theoretical foundations of continuous reinforcement learning, with a focus on addressing critical weaknesses in widely used algorithms like DDPG and A3C. His key research areas include stochastic differential equation methods, robot control, and autonomous driving systems. In his seminal 2019 work, "Incremental Reinforcement Learning," Chen identified that DDPG cannot effectively control noise in control processes, while A3C fails to satisfy continuity conditions under Gaussian policies. To resolve these issues, he proposed a novel continuous reinforcement learning framework grounded in stochastic differential equations, offering a more robust theoretical basis for real-world applications. Though his most-cited paper currently holds 5 citations, its impact lies in laying foundational groundwork for future improvements in continuous control. Chen's contributions are particularly notable for bridging gaps between theoretical rigor and practical deployment in safety-critical domains like autonomous driving, where noise management and policy continuity are paramount. His work continues to inspire researchers seeking mathematically principled approaches to reinforcement learning challenges.
Research Focus
Key Achievements
Top Papers
- 1