ECML talk series 2019

Title: Machine Learning for Optimal Decision Making under Uncertainty 

Speaker: Dr Vu Nguyen, University of Oxford
When: 10:30 - 11:30, Wednesday 16 August 2019
Where: 008.11.068

Abstract: 

The latest research in machine learning for sequential decision-making under uncertainty includes two common settings of immediate feedbacks and delayed feedbacks. In the first setting, the feedback is observed after each decision is made. The task is to make the optimal decision sequentially to achieve the highest feedback score. To make the optimal decision forth is problem, I will present a machine learning approach, called Bayesian Optimisation which views the relationship between decision-feedback through a black-box function to be optimised. In the second setting of delayed feedback, it is challenging that we may not see the feedback for each decision made. Instead, we make a sequence of decisions and only see the feedback in the future. This setting happens, for example, in Chess game. Despite of making multiple moves, the feedback of winning or losing is only available at the end of the game. I will present Deep Reinforcement Learning (DRL) to make the optimal decisions under delayed feedback. Then, I will share my recent research in DRL for financial promotion marketing and quantum Qubittuning. 

Speaker bio: 

Dr Vu Nguyen is currently a Postdoctoral Research Associate at the Machine Learning Research Group, University of Oxford. He is working with Professor Michael Osborne and Professor Andrew Briggs on a machine learning project for tuning quantum Qubit using Bayesian optimisation and deep reinforcement learning. Previously he was working as a Research Scientist at a Credit AI in Melbourne and was a postdoctoral researcher at Deakin University where he obtained his PhD in 2015. He was the recipient of ACML 2016 best paper award, IEEE ICDM 2017 best papers and one of the 200 young researchers world-wide for attending Heidelberg Laureate Forum 2015.