Project: Reinforcement Learning (RL) is a Machine Learning (ML) paradigm, used for decision-making tasks, where an agent learns to achieve a specified goal, by interacting with its underlying environment. Compared to the widely explored games (Chess, Go) and physics simulation problems (MuJuCo) in RL, real-world RL systems must contend with much more technical challenges. This project explores the State-Of-The-Art (SOTA) RL algorithms for Type 1 Diabetes with an aim to solve the continuous control problem of determining the amount of insulin delivery to the body to ensure glucose regulation. The SOTA RL algorithms include both Deep Learning (DL) and more traditional ML approaches.
Timeline:
- Background & Related Work. Learn about state-of-the-art (SOTA) RL algorithms and familiarize with our existing codebase (https://github.com/chirathyh/G2P2C). Then write a literature survey to explore the latest SOTA RL algorithms based on their applicability to the target problem.
- Coding & Experiments. Implement selected RL algorithms and conduct evaluation experiments for benchmarking.
- Bonus Item. Integrate developed algorithms into our demonstration system called CAPSML at https://capsml.com/ for others to try out your work.
- Conclusion. Thesis writing, potential publication writing, and code documentation.
Supervisors:
- Dr. Chirath Hettiarachchi (Research Fellow, School of Computing), a computer scientist working on ML and Reinforcement Learning algorithms to develop closed-loop treatment for clinical applications.
- Prof Klaus-Martin Schulte (Chair of Surgery, ANU College of Health and Medicine) is an academic general surgeon with expertise in Endocrine Surgery and Major Trauma Surgery.
- Prof. Hanna Suominen (Associate Director of JEI, Neuroinformatics), a computer scientist with 20 years’ of experience at forefront of bringing ML/DL algorithms, document analysis methods, and personalized medicine technologies to bear.
Requirements: To undertake substantial work on this project, students must have a solid background and very good skills in programming (Python, PyTorch) and ML/DL. To apply for this opportunity please forward your CV and transcript to Dr. Chirath Hettiarachchi (chirath.hettiarachchi@anu.edu.au). Successful candidates will be invited for a discussion to learn more about the project.