Markov decision processes and related processes have found an enormous number of applications in diverse fields, ranging from signal processing to control and machine learning, due to their simple structures as models of dynamical systems. In this talk, we will discuss some inverse problems related to these models, such as inverse filtering and counter-adversarial learning, where the goal is to reconstruct the sensor or the models used by an agent, based on its private belief or its actions. Solving these tasks is expected to lead to large improvements in data-driven reinforcement learning and control design, by relying on existing prior knowledge existing in the form of agent acting on a prescribed environment.
Cristian R. Rojas was born in 1980. He received the M.S. degree in electronics engineering from the Universidad Técnica Federico Santa María, Valparaíso, Chile, in 2004, and the Ph.D. degree in electrical engineering at The University of Newcastle, NSW, Australia, in 2008. Since October 2008, he has been with the Royal Institute of Technology, Stockholm, Sweden, where he is currently Associate Professor of the Division of Decision and Control Systems. His research interests lie in system identification, signal processing and machine learning. Dr. Rojas is a member of IEEE and the IEEE Technical Committee on System Identification and Adaptive Processing since 2013, and of the IFAC Technical Committee TC1.1. on Modelling, Identification, and Signal Processing since 2013. He is Associate Editor for the IFAC journal Automatica and for the IEEE Control Systems Letters (L-CSS).
Speaker: Cristian Rojas, Associate Professor Department of Automatic Control KTH
Chalmers machine learning seminars are organised by the division of
Data Science and AI and open to the public with speakers from both
academia and industry. Feel free to reach out to us if you have
something that you think would be interesting to present.
Emil Carlsson, caremil(at)chalmers.se
Arman Rahbar, armanr(at)chalmers.se
23 November, 2020, 14:00
23 November, 2020, 15:00