L2RPN 2020

Learning To Run a Power Network Challenge

Latest News

"L2RPN in a sustainable world" NeurIPS competition is now Open

Track Robustness: https://competitions.codalab.org/competitions/25426

Track Adaptability: https://competitions.codalab.org/competitions/25427

OPEN-submissions Prizes will be awarded by September 21rst and again on October 12th. Everyone can win, check it out.

Make sure to sign up in the mailing list to stay informed! You can also come discuss on our Discord Channel: https://discord.gg/cYsYrPT

A sandbox competition is already available for anyone to start playing around: https://competitions.codalab.org/competitions/24493

Also visit the Competitions section above for more information about the competitions. You can find there the WCCI winning team approach presentation.

Competition Overview & Mailing List


Power networks transport electricity across states, countries and even continents. They are the backbone of power distribution, playing a central economical and societal role by supplying reliable power to industry, services, and consumers. Their importance appears even more critical today as we transition towards a more sustainable world within a carbon-free economy, and concentrate energy distribution in the form of electricity. Problems that arise within the power grid range from transient brownouts to complete electrical blackouts which can create significant economic and social perturbations, i.e.de facto freezing society. Grid operators are still responsible for ensuring that a reliable supply of electricity is provided everywhere, at all times. With the advent of renewable energy, electric mobility, and limitations placed on engaging in new grid infrastructure projects, the task of controlling existing grids is becoming increasingly difficult, forcing grid operators to do “more with less”. This challenge aims at testing the potential of AI to address this important real-world problem for our future.

Full Challenge description Paper

(see also white paper in next section)


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

The NeurIPS competition will last until end of October 2020

AI For Smart Grids:

If you want participate to the competitions and get notified, especially when the competition starts, 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.


Introduction to Electricity Network Operation


Educational White Paper with the most important concept to get about Power System operation on the one hand and Reinforcement Learning on the other hand.

Recent IEEE Big data webinar introducing L2RPN challenge & more

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 ---->