NVIDIA Researchers Used Artificial Intelligence to Recreate PAC-MAN Without a Game Engine

[Tsing]

Image: NVIDIA



Would you believe that artificial intelligence has gotten sophisticated enough to recreate an entire game just by analyzing footage of it? That’s exactly what NVIDIA researcher Seung-Wook Kim and his collaborators pulled off with GameGAN, a powerful new neural network model that’s capable of emulating the original PAC-MAN experience without an underlying engine. The feat was made possible by the magic of generative adversarial networks, which form data by leveraging competing systems.



“This is the first research to emulate a game engine using GAN-based neural networks,” said Kim, the lead author on the project. “We wanted to see whether the AI could learn the rules of an environment just by looking at the screenplay of an agent...

Continue reading...

 

[LeRoy_Blanchard]

One step closer to skynet and the machines becoming self aware.

 

[Peter_Brosdahl]

One step closer to skynet and the machines becoming self aware.

That's o.k. I figured out a while back the solution would be to give cell phones to kill bots and teach them how to text and check social media. Could only imagine how much more quickly advanced AI could self destruct under those circumstances.

 

[LeRoy_Blanchard]

That's o.k. I figured out a while back the solution would be to give cell phones to kill bots and teach them how to text and check social media. Could only imagine how much more quickly advanced AI could self destruct under those circumstances.

Instead you'll be giving them the location and habits of all humans on the planet.

 

[Peter_Brosdahl]

Instead you'll be giving them the location and habits of all humans on the planet.

Yeah, but there'd be a factor of natural selection involved as well.