Yuya Sun
Papers
1
Total Citations
1
H-Index
1
About
Yuya Sun is a rising researcher in reinforcement learning and model-based policy optimization, whose work explores the intersection of control theory and machine learning. In their highly cited 2025 paper, "Coupled flows as guidance for model-based policy optimization," Sun introduces a novel framework that leverages coupled dynamical systems to improve the stability and efficiency of policy learning in complex environments. This contribution addresses a critical challenge in model-based reinforcement learning—balancing exploration and exploitation—by using flow-based guidance to steer policy updates. Though early in their career, Sun's work has already garnered attention for its theoretical elegance and practical potential, with the paper accumulating citations that signal growing influence. Their research promises to advance autonomous decision-making systems, from robotics to game AI, by providing more robust and sample-efficient learning algorithms. Sun's innovative approach to coupling model dynamics with policy optimization marks them as a promising voice in the next generation of AI researchers.
Research Focus
Key Achievements
Top Papers
- 1Coupled flows as guidance for model-based policy optimization1 citations · 2025