Model-free optimal control

Automated control in general and optimal control in particular typically rely on a good mathematical model of your system.

Unfortunately, some systems such as power grids or traffic systems are so big and complex that it is impossible to get an accurate model. What can you do?

Saverio Bolognani, winner of ETH’s Golden Owl teaching award, has an answer for you, brilliantly explained in his slides on Online feedback optimisation.

Blog
You cannot always be safe
You cannot always be safe

Risk management in automation - by Jonathan Hilberg

Madupite
Madupite

Solve bigger Markov Decision Processes in less time - by Matilde Gargiani

Model-free optimal control
Model-free optimal control

How to cope when your system is too complex to model

Stochastic optimal control
Stochastic optimal control

A way to find happiness? - by Claudia Fischer

Related articles