PhD in Reinforcement Learning, Privacy and Computation at Chalmers

This challenging project is involves reinforcement learning under privacy and computational constraints. The student will develop theory and algorithms to investigate the interaction between approximate inference and planning in constrained agents. The focus will be on agents that are trying to solve the reinforcement learning problem. On the theoretical side, this will be done by formalising computational limitations as approximate statistics or differential privacy constraints; two new areas in learning theory that are deeply connected to computational problems. Then we can obtain general bounds on problems with such constraints. We can also leverage approximate statistics to optimise the amount of computational effort used while planning, which will allow us to design efficient algorithms.
Position details:
The position is for 5 years, after a 1 year probation period, and includes 1 year of coursework and 1 year of teaching assistant work.
There is also a possibility for research visits at the SequeL group at INRIA-Lille, France and the Economics and Computer Science group at Harvard, USA.
Application website:
https://www.chalmers.se/en/about-chalmers/vacancie...
Deadline: 31 May 2017.