Dr Nan Ye
The University of Queensland

Reinforcement Learning – Theory, Algorithms and Applications

Reinforcement learning, a subfield of Artificial Intelligence (AI), has recently seen successful applications in various domains such as games, robotics, and mathematics. Notable breakthroughs include AlphaGo, a game AI that plays Go at a superhuman level, and AlphaTensor, an algorithm that discovers highly efficient record-breaking matrix multiplication algorithms.

This course begins with a gentle and intuitive introduction to the exciting field of reinforcement learning before delving deeply into the theory, algorithms, and applications. Students will gain both theoretical knowledge and practical skills.


  • Introduction and Overview
  • Classical reinforcement learning algorithms
  • Deep reinforcement learning
  • Advanced topics: stabilization, representation learning, few-shot learning
  • Applications

Requirements and Pre-requisites

This course assumes knowledge of basics of probability, statistics and programming. Knowledge on machine learning and/or deep learning is beneficial.


This course is broadly relevant to students intrigued by AI-powered applications such as game AIs, self-driving cars, robotic manipulation. It is particularly relevant to students who are interested in understanding the mathematics and algorithms of reinforcement learning, as well as those keen on conducting research in reinforcement learning or developing applications powered by this technology.

Dr Nan Ye

Dr Nan Ye
The University of Queensland

I am a Senior Lecturer in Statistics and Data Science in the School of Mathematics and Physics in University of Queensland. I obtained a double degree in applied mathematics and computer science, followed by a PhD specialising in probabilistic machine learning from NUS. I have previously held postdoc or visiting researcher positions at NUS, QUT, UC Berkeley.

I am interested in developing theoretically grounded and practical algorithms for learning and decision-making. I have published papers on topics including sequential decision making under uncertainty, weakly supervised learning, probabilistic graphical models, statistical learning theory, in venues such as NeurIPS, ICML, ICLR, UAI, JAIR, JMLR. I have received an IJCAI-JAIR Best Paper Prize in 2022, and a UAI Best Student Paper Award in 2014.