Past Event

About the Speaker

Dr Vu Nguyen

 Vu Nguyen is a Postdoctoral Research Associate in Machine Learning at University of Oxford. He is working with Prof. Mike Osborne in Machine Learning Research Group and Prof. Andrew Briggs.

Research Interests

• Bayesian Optimization, Gaussian Process, Deep Reinforcement Learning
• Bayesian Nonparametric, Multilevel Modelling

Abstract

The latest research in machine learning for sequential decision-making under uncertainty includes two settings of immediate feedbacks and delayed feedbacks. In the first setting, the feedback is observed after each decision is made. This relationship can be presented using a black-box function with decision-feedback. Our goal is to identify the optimal decision which is equivalent to optimising this black-box function. I will present a technique, called Bayesian Optimisation which recently gained tremendous success in scientific experimental designs and machine learning hyperparameter tuning.  In the second setting of delayed feedback, it is challenging that we may not see the feedback for each decision. Instead, we make a sequence of decisions and only see the feedback in the future. Our goal is to identify the best sequence of decisions for the best feedback. I will present Deep Reinforcement Learning (DRL) technique to solve this delayed feedback setting. Then, I will share one of my recent research in financial promotion marketing using DRL.

 

---

---