AI robots learned how to play horrible football all by themselves
We're developing AI that can learn for itself, and that's the real news from this story.
Key takeaways
- In order to learn how to play, AI researchers first used DeepMind’s state-of-the-art MuJoCo physics engine to train virtual versions of the robots in decades of match simulations.
- The simulated robots were rewarded if their movements led to improved performance, such as winning the ball from an opponent or scoring a goal.
- Previous DeepMind research on football-playing AI has used different team set ups, increasing the number of players in order to teach simulated humanoids how to work as a team.
Cite or link to this article
Griffin, M. (2024) 'AI robots learned how to play horrible football all by themselves', 311 Institute, 3 February. Available at: https://www.311institute.com/ai-robots-learned-how-to-play-horrible-football-all-by-themselves/ (Accessed: 1 October 2026).
Recently we saw Artificial Intelligence (AI) beating humans in real sports such as drone racing and whatever this sport is … and now, a year on from when AI robots took on humans at boxing, a team of AI powered robots developed by Google’s DeepMind have figured out how to play football. Like it’s that hard any way …
The miniature humanoid robots, which are about knee height, were able to make tackles, score goals and easily recover from falls when tripped. In order to learn how to play, AI researchers first used DeepMind’s state-of-the-art MuJoCo physics engine to train virtual versions of the robots in decades of match simulations.
The simulated robots were rewarded if their movements led to improved performance, such as winning the ball from an opponent or scoring a goal.
It's horrible but awesome!
Once they were sufficiently capable of performing the basic skills, DeepMind researchers then transferred the AI into real-life versions of the bipedal bots, who were able to play one-on-one games of football against each other with no additional training required.
“The trained soccer players exhibit robust and dynamic movement skills, such as rapid fall recovery, walking, turning, kicking and more,” DeepMind noted in a blog post.
“The agents also developed a basic strategic understanding of the game, and learned, for instance, to anticipate ball movements and to block opponent shots.
“Although the robots are inherently fragile, minor hardware modifications, together with basic regularisation of the behaviour during training led the robots to learn safe and effective movements while still performing in a dynamic and agile way.”
A paper detailing the research, titled ‘Learning agile soccer skills for a bipedal robot with deep reinforcement learning’, is currently under peer-review.
Previous DeepMind research on football-playing AI has used different team set ups, increasing the number of players in order to teach simulated humanoids how to work as a team.
The researchers say the work will not only advance coordination between AI systems, AKA Swarm AI, but also offer new pathways towards building Artificial General Intelligence (AGI) that is of an equivalent or superior level to humans.
What this means for your organisation
Simulation can replace live practice.
The robots first trained as virtual versions, using decades of match simulations. The learning was moved into real bipedal bots with no additional training required. Leaders should ask which of their own tasks could be rehearsed in a safe virtual setting first.
Rewards shape what systems learn.
The simulated robots were rewarded when their moves won the ball or scored a goal. They went on to anticipate ball movements and block opponent shots. What a system is rewarded for decides how it behaves, so reward design is a management choice.
Teamwork is the next step.
The researchers say the work will advance coordination between AI systems, known as Swarm AI, and offer new pathways towards Artificial General Intelligence. The paper is still under peer review, so treat these claims with care. Watch the work, but do not plan around it yet.
Three questions for your next leadership meeting
- Which of our tasks could be practised in simulation before real use?
- Who decides what our automated systems are rewarded for?
- How will we check claims that are still under peer review?
The trends and technologies behind this story
From the 311 Starburst, the 311 Strategic Intelligence Unit’s map of the technologies and trends shaping the next 50 years.
Analysis by the 311 Strategic Intelligence Unit, from Matthew Griffin’s article and 311 data. First published on Fanatical Futurist.
FAQ
Why does this matter?
We're developing AI that can learn for itself, and that's the real news from this story.
About the author
Matthew Griffin Founder, President and Futurist, 311 Institute
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath."
Read full bio
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath." 17-time best selling author of the "Codex of the Future" series, Matthew is the Founder, President and Futurist of the 311 Institute, a global Futures and Deep Futures advisory firm working with royal households, world leaders, G7, G20, and G77 governments, NGOs, and multi-national mid and mega cap firms to help them explore, shape, and lead the next 50 years of business and society.
An award-winning YouTube creator with over a million followers, with an unrivalled global reach and impact, Matthew is a highly sought-after international keynote speaker, lecturer, and mentor who collaborates with global leaders through the United Nations Alliance of Civilizations (UNAOC) and United Nations General Assembly (UNGA) to shape pivotal initiatives such as the UN’s AI for Humanity programme, the United Nations Conference of the Parties (UN COP), and the World Economic Forum in Davos.
As the former Global Head of Cloud, National Security, and Enterprise Sales for companies including Atos, Dell-EMC, and IBM, Matthew has a proven track record of building multi-billion dollar business units and turning failing divisions into market leaders. His ability to identify, analyse, and communicate the implications of hundreds of emerging technologies and trends is unparalleled, and his insights are trusted by many of the world’s most respected organisations, including ABB, Accenture, Adidas, AON, ARM, BCG, Centrica, Citi, Coca-Cola, Dentons, Deloitte, Dow Jones, EY, Google, KPMG, Lego, Legal & General, LinkedIn, Microsoft, PepsiCo, Qualcomm, RWE, Samsung, Siemens AG and Siemens Energy, T-Mobile, UBS, VISA, Walmart, Workday, Worldpay and many others.
Regularly featured in the global media including the AP, BBC, Bloomberg, CNBC, Discovery, Forbes, Khaleej Times, Telegraph, TIME, ViacomCBS, WIRED, and the WSJ, Matthews mission is to help organisations create a fair and sustainable future whose benefits are shared by everyone irrespective of their ability, background, or circumstances.
What future do you need to see?
Choose one to get started on robotics and the future of your organisation.
Sources and further reading
- whatever this sport engadget.com
- Op3 soccer sites.google.com
- 2304.13653 arxiv.org
Source: first published by the 311 Institute on 3 February 2024. Cite as: Griffin, M. (2024). AI robots learned how to play horrible football all by themselves. 311 Institute. https://www.311institute.com/ai-robots-learned-how-to-play-horrible-football-all-by-themselves/
You are welcome to quote this article with credit and a link to the original.