Hello, my name is Sonny! 🐣

About Me 📰

I am a PhD researcher at the University of Utah, studying reinforcement learning and continual learning to develop adaptive rehabilitation technologies.

My research focuses on how learning agents can build predictive representations of their environment and continually adapt their behavior in real-world rehabilitation settings. In particular, I study reinforcement learning architectures that leverage predictive representations of state from General Value Functions (GVFs) to support adaptive control and decision-making in dynamic environments.

I currently apply these ideas to rehabilitation technologies, such as assistive robotics for post-stroke ambulation. These systems must continually adapt to changing users and environments, and learn from multimodal sensor data including EMG signals, joint kinematics, and underfoot pressure.

More broadly, I am interested in research at the intersection of:

• Reinforcement Learning
• Continual Learning
• Predictive Representations (e.g., GVFs)
• Assistive Robotics

My goal is to develop reinforcement learning systems that can operate in the real world, that continually learn from experience, enabling adaptive human-machine partnerships that improve over time.