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
Geo-trax
Geo-trax

Extract georeferenced vehicle trajectories from drone videos - by Robert Fonod

When you do not know how the world will react
When you do not know how the world will react

Use distributionally robust Stackelberg games to make decisions - by Zheyu Wu

The Recipe for Adapting
The Recipe for Adapting

Meta-learning, the secret to fast recalibration of controllers - by Salma Elfeki

When Water Meets Lithium
When Water Meets Lithium

Can batteries support Run-of-River power plants during periods of low electricity prices? - by Yannick Schüpbach

The Coke vs. Pepsi Battle
The Coke vs. Pepsi Battle

A computational approach to uncover hidden opinion dynamics - by Michelle Egger

Know Thy Voltage
Know Thy Voltage

Using real-time sensors to detect early warning signs of power grid instability - by Ioannis Papadopoulos

SIMBa
SIMBa

System Identification Methods leveraging Backpropagation - by Muhammad Zakwan

Splitting for planning
Splitting for planning

A divide-and-conquer approach to plan under constraints - by Panagiotis Grontas

A tale of bold flight and gentle landings
A tale of bold flight and gentle landings

Strategy guidance for teaching robots to stay within safe bounds - by Nicholas Behr

A game plan for electricity
A game plan for electricity

How smart incentives can keep the grid stable - by Jonas Matt

Stop overplanning!
Stop overplanning!

Optimising long-term decisions using short-term insights - by Junan Lin

No model? Call SoS!
No model? Call SoS!

Using SoS optimisation to find a robust controller for unknown systems - by Caroline Gärtner

Playing tag with robots
Playing tag with robots

Real-time tracking under real-life constraints - by Anastasis Vlachos

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