Guan-Horng Liu
Papers
1
Total Citations
17
H-Index
1
About
Guan-Horng Liu is a researcher at the forefront of control theory and machine learning, with a primary focus on bridging stochastic optimal control (SOC) and variational inference. His most impactful contribution is the development of a generalized framework for Variational Inference-Model Predictive Control (VI-MPC) using the non-extensive Tsallis divergence. By incorporating the deformed exponential function into the optimality likelihood, Liu’s work provides a principled way to interpolate between existing control schemes, offering greater flexibility and robustness in planning under uncertainty. This key paper, "Variational Inference MPC using Tsallis Divergence" (2021), has garnered 17 citations, establishing a foundation for more adaptive and efficient model-based reinforcement learning. Liu’s research is notable for its elegant mathematical unification of information geometry and control, making his work essential reading for students and researchers interested in the intersection of optimal control, entropy-based inference, and robotics. His contributions are paving the way for more resilient decision-making algorithms in complex, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1Variational Inference MPC using Tsallis Divergence17 citations · 2021