Skip to main content

Google’s DeepMind is training Waymo’s self-driving cars like StarCraft II bots

DeepMind is teaming up with Waymo, a fellow unit of Google parent Alphabet, to train self-driving cars, using the same method that was created to teach artificial intelligence bots how to play StarCraft II.

Waymo’s self-driving vehicles utilize neural networks to carry out tasks such as detecting objects on the road, predicting how other cars will behave, and planning its next moves. Training the neural networks has required “weeks of fine-tuning and experimentation, as well as enormous amounts of computational power,” DeepMind said in the blog post where it announced the collaboration with Waymo.

DeepMind and Waymo joined forces to create a more efficient process of training and refining the algorithms of self-driving vehicles, utilizing population-based training. This technique, inspired by the concept of biological evolution, speeds up the learning process for neural networks by focusing on the “fittest” specimens, which are the A.I. models that are the most efficient in carrying out tasks.

DeepMind principal research scientist Oriol Vinyals, who is also one of the inventors of population-based training, told the MIT Technology Review that the idea of using the technique to train self-driving cars was born when he visited Matthieu Devin, director of machine learning infrastructure at Waymo.

Vinyals and his colleagues first developed population-based training as a way to speed up the learning process of computers in playing StarCraft II. The real-time strategy game features the complexities of simultaneously managing resources, building structures and units, and controlling an army to beat opponents.

If population-based training is capable of teaching A.I. agents to play StarCraft II, then it will also be able to train neural networks to handle the different decisions that are required to maintain the safety and proper operation of self-driving vehicles.

On the surface, DeepMind’s work on artificial intelligence appears to only work for video games, with titles such as StarCraft II and Quake III. However, the unit is only utilizing these games as a learning environment, with Quake III‘s Capture the Flag mode showing that multiple A.I. agents are capable of learning and acting independently for cooperation or competition with other agents.

DeepMind’s population-based training has been applied to several models of Waymo’s self-driving vehicles, promising further improvements to the technology.

Aaron Mamiit
Aaron received a NES and a copy of Super Mario Bros. for Christmas when he was 4 years old, and he has been fascinated with…
How to clean a mouse pad — the right way
The Glorious Model O 2 Pro mouse sitting on a desk.

Even the latest and most "exciting" mouse mats can get dirty after long-term use. So it's a good idea to clean your mouse pad now and again — it not only looks better but it's more hygienic, too.

Here's how to clean your mouse pad to get it back to near-new condition.

Read more
Intel responds to reported laptop CPU instability problems
msi gt77 titan 2023 review 19

Update: Intel has provided Digital Trends with the following statement about CPU instability affecting mobile processors:

"Intel is aware of a small number of instability reports on Intel Core 13th/14th Gen mobile processors. Based on our in-depth analysis of the reported Intel Core 13th/14th Gen desktop processor instability issues, Intel has determined that mobile products are not exposed to the same issue. The symptoms being reported on 13th/14th Gen mobile systems – including system hangs and crashes – are common symptoms stemming from a broad range of potential software and hardware issues. As always, if users are experiencing issues with their Intel-powered laptops we encourage them to reach out to the system manufacturer for further assistance."

Read more