Title: Reinforcement Learning

Date: 28-Jun-19

Location:

Speaker: Reinforcement Learning

Abstract: Reinforcement Learning (RL) is a relevant and timely area of research which is nowadays receiving a significant level of attention not only from academia, but also from industry actors, with organizations such as Google Deepmind or OpenAI investing large amounts of money in developing new RL algorithms and solutions. From a scientific perspective, RL is the point of confluence of different academic disciplines, such as Optimal Control, Machine Learning, Software Agents or even Computational and Behavioral Psychology. Succinctly, in an environment where (software) agents interact with ta dynamic environment, RL attempts to learn policies that map states to actions with the goal of maximizing a cumulative (long-term) reward. RL is viewed today as one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Motivated by previous description, the goal of this talk is to present a brief (and kind) introduction to the basics and foundations of RL.

Bio: Sergio Rozada is a data scientist at BBVA. He holds a MSc in Data Science at City, University of London and a BSc in Electronics and Automation Engineering at the University of Oviedo. For two years, he worked as a researcher at ArcelorMittal participating in projects related to applied robotics and applied additive manufacturing in industrial environments. Currently, he is developing data-based algorithms for Personal Financial Management (PFM) products at the BBVA Client Solutions Department.