Machine learning researcher working on sequential decision-making, scientific ML, and computational methods for biomedical systems.
I build learning and simulation systems for complex biological dynamics, including reinforcement learning for closed-loop insulin delivery and neuromodulation.
- NeuroStimEnv — biophysical neural simulation + EEG + transcranial stimulation + reinforcement learning.
- RL4T1D — research infrastructure for reinforcement learning in Type 1 Diabetes.
- G2P2C — reinforcement learning with glucose prediction and planning for automated insulin delivery.
- GluCoEnv — simulation environment for RL-based glucose control.
Research: Reinforcement Learning · Sequential Decision-Making · Scientific ML · Dynamical Systems · Computational Neuroscience