255 citations · 1.2k across the 88 of their papers we have counts for
Showing 2022 · math.OCShow all
2 papers · 2 filters
math.OC2022
How are policy gradient methods affected by the limits of control?
Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg +1
We study stochastic policy gradient methods from the perspective of control-theoretic limitations. Our main result is that ill-conditioned linear systems in the sense of Doyle inev…
math.OC2022
Scale Fragilities in Localized Consensus Dynamics
Emma Tegling, Bassam Bamieh, Henrik Sandberg
We consider distributed consensus in networks where the agents have integrator dynamics of order two or higher (). We assume all feedback to be localized in the sense that…