06-04, 15:45–16:25 (Europe/London), Warwick
Reinforcement learning (RL) has become the go-to framework when working with decision processes. Originally demonstrating superhuman performance in videogames, applications of reinforcement learning providing state-of-the-art results now extend to a myriad of areas: from drug discovery to autonomous driving and computer vision, just to name a few.
In this talk, we will concentrate on the application of RL to pricing environments. In particular, we will consider how Ben, our friendly neighbourhood gelato merchant, might approach the dynamic problem of pricing his products throughout the year with RL. We will introduce the problem as a Markov decision process and review the most common archetypes of RL algorithms to solve it while highlighting various pitfalls and challenges, always with a focus on its implementation to pricing.
By the end of the talk, we will be able to help Ben set up a pricing model for his delicious gelato!
The talk is aimed at an introductory level for people with an interest in RL and/or pricing/optimisation problems. Thus, while a basic knowledge of deep learning/reinforcement learning would be beneficial it is not necessary.
The main goal is for everyone to get something from this talk. Someone without any experience will get an understanding of the basics of RL from a bird’s eye view. While someone more experienced might find more interesting our discussion around some of the hurdles we encountered in implementing RL solutions in practice.
We will update this description with a link to the code used for the talk once it is open sourced.
No previous knowledge expected
After 7 years of academic research experience in string theory and cosmology, Cesc brings his unique blend of expertises to Data Science. With a keen interest in machine learning, optimisation problems and pricing, Cesc has been leading the Reinforcement Learning capabilities of the Data Science team at Tesco.