Model-based and hybrid multiagent reinforcement learning in Internet of Things
Prof Tansu Alpcan
Dr Sarah M. Erfani
School / Faculty:
School of Electrical and Electronic Engineering
Faculty of Engineering and Information Technology
Building an intelligent system that takes decisions by itself offers several benefits including flexibility and scalability. However, the training of such a system requires significant time and huge computational resources. My PhD research aims to reduce the computational burden of intelligent systems by taking advantage of domain knowledge in internet of things.
Q & A
Why did you decide to do a PhD?
I love teaching students and to stay abreast with the latest literature in my field. Both of these led me to get started with my PhD.
What do you enjoy reading?
Surprise: Not the research papers 😉 I like unpredictability so enjoy reading suspense and thrillers.
What do you enjoy doing when you're not working on your PhD?
Exploring kids-centric activities and spending quality time with my two munchkins.
Name one fun fact about you.
Studied in three different continents on full scholarships. Undergraduate studies in Asia, masters in North America, and PhD in Australia/Oceania.
Work and Publications
Domain-aware multiagent reinforcement learning in navigation
A portable benchmark suite for highly parallel data intensive query processing
Distributed nonlinear model predictive control and reinforcement learning
A portable relational algebra library for high performance data-intensive query processing