Timezone: »
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a numbers of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize a quadratic reward function. We present a method to optimize the expected value of the reward over the posterior distribution of the unknown system parameters, given data. The algorithm involves sequential convex programing, and enjoys reliable local convergence and robust stability guarantees. Numerical simulations and stabilization of a real-world inverted pendulum are used to demonstrate the approach, with strong performance and robustness properties observed in both.
Author Information
Jack Umenberger (Uppsala University)
Thomas Schön (Uppsala University)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Spotlight: Learning convex bounds for linear quadratic control policy synthesis »
Thu. Dec 6th 09:10 -- 09:15 PM Room Room 220 CD
More from the Same Authors
-
2021 Poster: Stabilizing Dynamical Systems via Policy Gradient Methods »
Juan Perdomo · Jack Umenberger · Max Simchowitz -
2019 Poster: Robust exploration in linear quadratic reinforcement learning »
Jack Umenberger · Mina Ferizbegovic · Thomas Schön · Håkan Hjalmarsson -
2019 Spotlight: Robust exploration in linear quadratic reinforcement learning »
Jack Umenberger · Mina Ferizbegovic · Thomas Schön · Håkan Hjalmarsson -
2017 Poster: Linearly constrained Gaussian processes »
Carl Jidling · Niklas Wahlström · Adrian Wills · Thomas Schön -
2014 Poster: Sequential Monte Carlo for Graphical Models »
Christian Andersson Naesseth · Fredrik Lindsten · Thomas Schön -
2013 Poster: Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC »
Roger Frigola · Fredrik Lindsten · Thomas Schön · Carl Edward Rasmussen -
2012 Poster: Ancestor Sampling for Particle Gibbs »
Fredrik Lindsten · Michael Jordan · Thomas Schön