Sipeng Wang
Papers
1
Total Citations
3
H-Index
1
About
Sipeng Wang is a rising researcher in the field of intelligent control systems and reinforcement learning, with a focus on applying deep neural networks to complex, nonlinear dynamical systems. His most cited work, "Balance Controller Design for Inverted Pendulum Considering Detail Reward Function and Two-Phase Learning Protocol" (2024, 3 citations), addresses the fundamental challenge of stabilizing inherently unstable systems. Wang’s key contribution lies in developing an end-to-end deep neural network controller that directly maps system states to control commands, bypassing traditional model-based approaches. He introduced a novel two-phase learning protocol combined with a meticulously designed reward function, enabling efficient training of the neural network to achieve robust balance control. This work demonstrates his expertise in bridging reinforcement learning theory with practical control engineering, offering a scalable framework for autonomous decision-making in robotics and automation. Though early in his career, Wang’s innovative approach to reward shaping and phased learning has already garnered attention, positioning him as a promising contributor to the advancement of intelligent, data-driven control systems.
Research Focus
Key Achievements
Top Papers
- 1