Single Review on past events

Tobias Sutter (Research Fellow / Computer and Information Science) gave a talk entitled "Machine learning for dynamical systems".

Abstract:

Given the recent progress in information technology with real-time data being available at large scale, many complex tasks involving dynamical environments are addressed via tools from machine learning, control theory and optimization. While control theory in the past has mainly focused on model based design the advent of large scale data sets raises the possibility to analyse dynamical systems on the basis of data rather than analytical models. From a machine learning perspective, one of the main challenges going forward is to tackle problems involving dynamical systems which are beyond static pattern recognition problems. In this talk, I will give an overview about different problems lying in this intersection of dynamical systems, learning and control that I have worked on in the past. One such problem is reinforcement learning, which basically aims to learn an optimal policy from data by cleverly interacting with an unknown dynamical system described as a Markov Decision Process.