Graphics card manufacturer NVIDIA has been doing research on artificial intelligence and recently taught its AI system to recreate the game Pac-Man just by watching it being played. No coding or pre-rendered images were used for the software to base the recreation on. The AI model was simply fed visual data of the game being played alongside controller inputs. From there, the AI recreated what it saw frame by frame, resulting in a playable version of Bandai Namco‘s most recognizable title.
“It learns all of these things just by watching,” NVIDIA’s Rev Lebaredian, vice president of simulation technology, stated in a briefing. “[It’s] similar to how a human programmer can watch many episodes of Pac-Man on YouTube and infer what the rules of the games are and reconstruct them.”
Although it’s not a perfect recreation of the title and all its assets, all the mechanics and gameplay goals are the same. NVIDIA even believes this is how AI will be applied to game creation in the future. Lebaredian also notes the experiment was done in collaboration with Bandai Namco as it celebrates the 40th anniversary of the classic arcade game. “Eventually we’d like it to learn the rules of the real world,” says Lebaredian. NVIDIA proposes the AI could even learn how to navigate a warehouse by watching videos of a robotic trolley and use that to design its own navigation software.
Trained on 50,000 episodes of PAC-MAN, a new #AI model created by NVIDIA Research called GameGAN re-created the game environment in just days. Celebrate the #pacman40th anniversary and see how GameGAN puts an AI spin on this classic game. https://t.co/zOoioy0MU9 @BandaiNamcoUS pic.twitter.com/nyrXp9xhdA
— NVIDIA (@nvidia) May 22, 2020
The artificial intelligence program is called GameGAN, with GAN standing for “generative adversarial network,” which is a common architecture used in machine learning. GAN works by attempting to replicate input data while also comparing its work to the original source. If the two don’t match, the data is rejected and the program looks for improvements and tries again.
Although AI programs have generated virtual gaming spaces before, GameGAN is able to use a “memory module” that allows the program to store an internal map of the digital space it’s trying to recreate, leading to a more consistent copy.
Sanja Fidler, director of Nvidia’s Toronto research lab states that GameGAN was trained on over 50,000 episodes in order to recreate Pac-Man, but the AI agent was so good at the game that it almost ever died. “That made it hard for the AI trying to recreate the game to learn the concept of dying,” said Fidler.
NVIDIA says it will be releasing the recreated game online in the near future.
In other gaming news, Call of Duty: Warzone season four has teased the return of Captain Price.
— The Verge (@verge) May 22, 2020