Man City launch AI football competition with Google
Written by Simon Austin — October 13, 2020
MANCHESTER CITY have teamed up with Google Research to launch an AI football competition which they hope will ‘test and refine’ tactical principles on the pitch.
The competition is in the 'Google Research Football Environment' and participants will use code to control one player - an 'AI agent' - in a “physics-based 3D football simulation,” with the objective of scoring goals.
An AI agent is an entity programmed by an algorithm enabling it to perceive its environment, think intelligently and then act upon this environment.
Football has been a notoriously difficult environment for AI agents, because it's so complex and unpredictable. In the words of City and Google, “the sport requires a balance of short-term control, learned concepts such as passing, and high-level strategy, which can be difficult to teach agents.”
In this competition, the AI agent will either be the player with the ball in possession, or the one closest to the ball out of possession. Participants are able to submit up to five agents per day and will compete on a leaderboard, with the eventual winner getting a prize of $3,000.
This may all sound like gaming rather than real-life football, but City hope the competition can “offer new insights into the strategies of the world's most-watched sport.”
Brian Prestidge, Director of Data Insights & Decision Technology at City Football Group, said: “Football is a tough environment to perform in and an even tougher environment to learn in.
“Learning is all about harnessing failure, but failure in football is seldom accepted. Working with Google Research’s physics-based football environment provides us with a new place to learn through simulation and offers us the capabilities to test tactical concepts and refine principles so that they are strong enough for a coach to stake their career on.”
“We are looking forward to the opportunity to support some of the most creative and successful competitors through funding and exclusive prizes.
“We hope to establish ongoing collaboration with the winners beyond this competition, and that it will provide us all with the platform to explore and establish fundamental principles of football tactics, thus improving our ability to perform and be successful on the pitch.”
Greg Swimer, Chief Technology Officer at City Football Group, added "Technologies such as Machine Learning and Artificial Intelligence have huge future potential to enhance the understanding and enjoyment of football for players, coaches and fans.
“We are delighted to be collaborating with Google's research team to help broaden the knowledge, talent, and innovation working in this exciting and transformational area".
City have been investing heavily in their data science department since the start of the summer in a bid to close the gap with market leaders Liverpool.
Ravi Mistry joined in June as Football Intelligence Officer to "lead the analytical development of our practitioners and advance our football intelligence capabilities".
John-Mark Sisman arrived a month later as Performance Physicist and Chris Baker joined Prestidge’s team as a data-driven scouting co-ordinator in August.
Now the club is advertising for both a computer scientist and AI scientist, which would take the headcount in Prestidge's department up to six - the same number as in Ian Graham’s research team at Liverpool.