Last month, you may have seen that a group of researchers created a machine learning system that could transform the presentation of Grand Theft Auto V into something that looks almost photorealistic. It turns out, at about the same time, another group of AI enthusiasts were working on something even more impressive involving Rockstar's open world title. On Friday, YouTuber Harrison Kinsley shared a video showing off GAN Theft Auto, a neural network that can generate a playable stretch of Grand Theft Auto V's game world on its own. Kinsley and collaborator Daniel Kukieła made GAN Theft Auto with GameGAN, which last year recreated Pac-Man by watching another AI play through the game. GameGAN, as the name suggests, is a generative adversarial network.

Nvidia is best known for its graphics cards, but the company conducts some serious research into artificial intelligence, too. For its latest project, Nvidia researchers taught an AI system to recreate the game of Pac-Man simply by watching it being played. There's no coding involved, no pre-rendered images for the software to draw on. The AI model is simply fed visual data of the game in action along with the accompanying controller inputs and then recreates it frame by frame from this information. The resulting game is playable by humans, and Nvidia says it will be releasing it online in the near future.

This is episode #5 of the video series "Game Futurology" covering the paper "Learning to Simulate Dynamic Environments with GameGAN" by Seung Wook Kim, Yuhao Zhou, Jonah Philion, Antonio Torralba and Sanja Fidler. Game Futurology: This is a video series consisting of short 2-3 minute overview of research papers in the field of AI and Game Development. This series aims to ponder over what the future games might look like based on the latest academic research going on in the field today. Abstract: Simulation is a crucial component of any robotic system. In order to simulate correctly, we need to write complex rules of the environment: how dynamic agents behave, and how the actions of each of the agents affect the behavior of others.

Simulation is a crucial component of any robotic system. In order to simulate correctly, we need to write complex rules of the environment: how dynamic agents behave, and how the actions of each of the agents affect the behavior of others. In this paper, we aim to learn a simulator by simply watching an agent interact with an environment. We focus on graphics games as a proxy of the real environment. We introduce GameGAN, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training.

Pac-Man turns 40 today, and even though the days of quarter-munching arcade machines in hazy bars are long behind us, the legendary game's still helping to push the industry forward. On Friday, Nvidia announced that its researchers have trained an AI to create working Pac-Man games without teaching it about the game's rules or giving it access to an underlying game engine. Nvidia's "GameGAN" simply watched 50,000 Pac-Man games to learn the ropes. That's an impressive feat in its own right, but Nvidia hopes the "generative adversarial network" (GAN) technology underpinning the project can be used in the future to help developers create games faster and train autonomous robots. "This is the first research to emulate a game engine using GAN-based neural networks," Nvidia researcher Seung-Wook Kim said in a press release.

When Pac-Man hit arcades on May 22nd 1980, it held the record for time spent in development having taken a whopping 17 months to design, code and complete. Now, 40 years later to the day, NVIDIA needed just four days to train its new GameGAN AI to wholly recreate it based only on watching another AI play through. Dubbed GameGAN, it's a generative adversarial network (hence, GAN) similar to those used to generate (and detect) photo-realistic images of people that do not exist. The generator is trained on a large sample dataset and then instructed to generate an image based on what it saw. The discriminator then compares the generated image to the sample dataset to determine how close the two resemble one another.