L2RPN 2020

Learning To Run a Power Network Challenge

Upcoming Competitions - Starting In

Competitions will be held on Codalad challenge platform: https://competitions.codalab.org/competitions/

Also visit the Competitions section above for more information about them


Following the success of the Horizon prize to predict flows in the French long distance high voltage electricity transmission grid, managed by the company “Réseau de Transport d’Électricité” (RTE), we are organizing a new challenge. The goal of this challenge is to test the potential of Reinforcement Learning (RL) to control electricity transportation in power grids, while keeping people and equipment safe. Hence, it is the "gamification" of a serious problem: operating the grid is becoming increasingly complex because of the advent of less predictable renewable energies, the globalization of energy markets, growth in consumption and concurrent limitations on new line construction. To make smart grid happen, it is becoming urgent to optimize more tightly the grid operation, considering a broader range of topological changes used more frequently, without compromising security.

Grid2Operate AI for power grid framework

Our testbed platform used in competitions to model real-time operations, run & benchmark control algorithms github.com/rte-france/Grid2Op

AI For Smart Grids:

If you want to join us within this new community and participate to the competitions, please sign up to our mailing list.

If you first want to know more about it, go through this web page and our white paper below.

Will you help rejuvenate our aging Electricity Fairy ?

The Electricity Fairy Paintaing in Paris


White Paper

This paper explains in simple terms the different necessary concepts of a power grid and power grid operations, and to highlight upcoming challenges on which RL could help. An interactive tutorial on grid operations is available in the Power Grid in Action section.


Presented at Neurips 2018 workhop - Challenge into the wild

The Learning to run a power network challenge was first presented at the CIML workshop at Neurips 2018. It introduces the upcoming challenges for power grid operations.

A control room to operate a power grid in France

L2RPN DeepArt Logo


The Learning To Run Story

Previously on Learning to Run ...

A first Reinforcement Learning challenge organized at NeurIPS 2017 by Stanford caught our attention and inspired us: The Learning To Run Challenge - or how to learn a controller to make an agent walk and run without falling! This was a tough coordination and planning problem.

See the video for some fun and some impressive results obtained with RL! For more details, visit the github page.

... Coming soon on Learning to Run !

A power grid can be seen as well as a giant artificial body that needs to be controlled with coordination to ensure proper stability while operating under a challenging hazardous environment. Otherwise the system will fall into a BLACKOUT !

See a didactic video explaining a near blackout event in Europe in 2006. Visit this section to know more about real-world issues.

----> To continue diving into the world of power grids, make sure to visit other interactive sections available on top  ---->