no code implementations • 24 Nov 2020 • Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud
In this paper, we investigate the global convergence of gradient-based policy optimization methods for quadratic optimal control of discrete-time Markovian jump linear systems (MJLS).
1 code implementation • L4DC 2020 • Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud
We implement the (data-driven) natural policy gradient method on different MJLS examples.
no code implementations • 10 Feb 2020 • Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud
Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning.