The Technology section is powered by Favbet Tech
Google DeepMind and the Premier League club “Liverpool” have created a prototype of TacticAI artificial intelligence model for football training. The DeepMind lab, which has previously used AI for complex board games like Go, notes that AI can be trained on patterns seen on sports fields.
An artificial coach’s proposed improvements to players’ positioning during corner kicks, a big potential source of goals, have mostly been approved by human experts, according to a paper published in Nature. Currently, the technology can provide advantages in planning situations with predictable initial conditions, such as in the case of corners. The global challenge is to apply AI to more variable open game settings.
The DeepMind project is the result of three years of work with Liverpool. DeepMind’s model uses deep geometric learning on a dataset that includes 7,176 corners from the English Premier League between 2020 and 2023. The model learned to predict which player will touch the ball first after taking a corner. In tests, the ball receiver was among TacticAI’s top three candidates 78% of the time. Corner kicks together with free kicks according to statistics give up to 30% of all goals.
TacticAI analyzed the results of corner kicks with different player configurations and suggested positional improvements. Their usefulness was evaluated in a blind test conducted by five experts: three data specialists, one video analyst and one assistant coach. The experts could not distinguish the generated AI scenarios from real situations, preferring TacticAI’s advice over existing strategies 90% of the time.
Google DeepMind’s Petar Velichkovic says the research has broader applications beyond sports. “If we can model the game of soccer, we can also model several aspects of human psychology. As AI becomes more capable, it needs to better understand the world, especially in the face of uncertainty. Our system is able to issue decisions and suggestions under conditions of uncertainty. These skills, we believe, will be transferable to future AI systems, so this is a good testing ground,” he says.
Nvidia artificial intelligence is able to turn game characters into chatbots – NPCs with “unique” interaction
Sources: Financial Times, New Scientist
The Technology section is powered by Favbet Tech
Favbet Tech is an IT company with 100% Ukrainian DNA, which creates perfect services for iGaming and Betting using advanced technologies and provides access to them. Favbet Tech develops innovative software through a complex multi-component platform capable of withstanding huge loads and creating a unique experience for players. The IT company is part of the FAVBET group of companies.
The competition of ITS authors is ongoing. Write an article about game development, gaming and gaming devices and win a professional Logitech G923 Racing Wheel or one of the low-profile Logitech G815 LIGHTSYNC RGB Mechanical Gaming Keyboard!
