AI beats the world’s best players at Gran Turismo – and could change the future of driving
Your support helps us to tell the story
From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.
At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.
The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.
Your support makes all the difference.An artificial intelligence system has beaten some of the world’s best players at Gran Turismo – and could change the future of driving and other technologies.
The system was able to drive exceptionally fast, control its car and demonstrate good tactics even while keeping up on race etiquette, the researchers behind the breakthrough say.
Driving skills are among those that are most challenging, and most useful, to an AI. They require the driver to understand the complexities of the car and of how other people might drive.
As such, the findings could help inform future autonomous driving systems, as well as other artificial intelligence research, the authors of the new paper say.
Gran Turismo is also the latest game that AI has demonstrated its capabilities with – which in the past has included more traditional competitions, such as chess and poker.
The system, called GT Sophy, was trained using a technique called deep reinforcement learning. That saw it gradually learn how to accelerate and brake efficiently, pick its racing line, and deal with tactics from other drivers.
It then raced in head-to-head competitions against four of the world’s best drivers, across a range of different cars and tracks, and was able to beat them.
The research is detailed in a new paper, ‘Outracing champion Gran Turismo drivers with deep reinforcement learning’, published in Nature.
Join our commenting forum
Join thought-provoking conversations, follow other Independent readers and see their replies
Comments