The use of Contextual Bandits and Reinforcement Learning for improving products

In this tech talk you will learn:
Reinforcement learning has led to remarkable empirical results in fields like autonomous vehicles, gaming, and robotics. Join our speaker, Ph.D. Reshmi Ghosh from Carnegie Mellon University, in this tech talk about the state-of-the-art in contextual bandits and reinforcement learning.
You will learn the high-level mathematical formulation of contextual bandits and reinforcement learning. Then you will learn the essential probabilistic concepts required to formulate Reinforcement learning problems. The last section will cover publicly available examples from Microsoft and Wayfair. You will understand how these companies use Reinforcement Learning and Contextual Bandits in real-life cases.

Our speaker is Reshmi Ghosh. She is currently a Data and Applied Scientist at Microsoft's AI Development team at the New England Research and Development center and researches the state-of-the-art Machine and Deep Learning methods to accelerate product development and improve customer experience. Prior to joining Microsoft, Reshmi completed her Ph.D. at Carnegie Mellon University, where she worked on developing mitigating strategies for climate change impact on society using large-scale deep learning models on terabytes of open-source datasets. Reshmi is passionate about causal inference, reinforcement learning, and making machine learning applications engineering-friendly for edge devices.