Thanh Thi Le
Papers
1
Total Citations
8
H-Index
1
About
Thanh Thi Le has made significant contributions to the field of reinforcement learning and robotics, with a particular focus on optimal control for unstable dynamical systems. Their most cited work investigates on-policy and off-policy Q-learning algorithms for two-wheeled inverted pendulum (TWIP) robots, addressing the critical challenge of controlling these inherently unstable systems when dynamic models are uncertain or unknown. By developing and comparing both learning paradigms, Le demonstrated that these model-free approaches can achieve optimal control performance, ensuring stability and robustness even without precise system knowledge. This research, with 8 citations, represents an important step in bridging theoretical reinforcement learning algorithms with practical robotic applications. Le’s work is particularly valuable for researchers and students interested in adaptive control, autonomous systems, and the application of Q-learning to real-world robotics challenges where traditional model-based methods fall short. Their contributions highlight the growing importance of data-driven control strategies in modern robotics and automation.
Research Focus
Key Achievements
Top Papers
- 1