Pac-Man just turned 40 years old and to help mark the anniversary, there’s a new version of Monopoly centered around the iconic character. It includes a digital banking unit that doubles as a mini arcade game you play whenever you pass Go.

You’ll play for points instead of cash in Monopoly Arcade Pac-Man, and you can earn some more through mini-games on the banking unit. You can use your points to buy levels (aka properties). Each player will have a plastic arcade coin they can insert into the banking unit to check their points; buy, sell or steal levels; and pay rent as well as play the mini-games.

Last week, Bandai Namco announced that it had turned the neon-infused hit Pac-Man: Championship Edition into an NES-style demake. At the time, it seemed as if you could only play the game if you bought all of the entries in the company’s Japanese Namcot Collection series of re-releases. However, the game will be included as a bonus in the upcoming Namco Museum Archives Vol. 1, which will be available for consoles and Steam in North America and Europe on June 18th.

The collection also includes arcade titles like Dig-Dug and Xevious, as well as the cult classic Famicom title Splatterhouse: Wanpaku Graffiti. It will be joined by Namco Museum Archives Vol. 2, which features ten games from a slightly newer era, like Galaga, Pac-Land and Super Xevious. This compilation will come with an NES-style version of Gaplus as a bonus — a game that was previously only on the Commodore 64 and in arcades.

In GameGAN’s case, the generative network was trained using 50,000 play sessions of the game and then told to recreate it as a whole, from the static walls and pellets to the ghosts, Pac-Man himself and the rules governing their interactions. The entire process ran on a quartet of GP100s. GameGAN was not, however, provided with any of the underlying code or access to the game’s engine. Much like learning the rules by peering over your older brother’s shoulder as he played, GameGAN figured out Pac-Man based solely through watching the onscreen action and following the controller inputs as a separate AI played the game. 

“There have been many AIs created in recent years, that can play games, they’re agents within these games,” Rev Lebaredian, NVIDIA’s VP of simulation technology, told Engadget. “But this is the first GAN that’s been created that can actually reproduce the game itself as a black box.”  

As an NVIDIA blog posted on Friday explains, “As an artificial agent plays the GAN-generated game, GameGAN responds to the agent’s actions, generating new frames of the game environment in real time. GameGAN can even generate game layouts it’s never seen before, if trained on screenplays from games with multiple levels or versions.“

This is a similar creation process to procedural generation techniques, which have been around since the late ‘70s, but a far more efficient method. “So if you can think about the work that goes into creating a game like Pac-Man,” Lebaredian said. “There’s a programmer that has to sit there and really think about all of the roles and how they’re going to exactly describe the creation of this game, the creation of the maze and the interaction of all of the agents within that game. It’s painstaking work.” 

“What this can help with is, we can have the GAN just learn what all of those rules are by observing,” he continued. “Ideally we would teach something like this GameGAN what the procedural rules are for the worlds you want to create.”

This could be as simple as, say, strapping a video camera to a car’s dashboard and going for a drive. GameGAN would be able to train on that video data and generate realistic, procedurally generated levels based on what the camera has seen.

This technique could also improve the development times of real-world autonomous machines. Since the robots employed in warehouses and on assembly lines can pose a threat to the safety of their human coworkers, these machines are typically first trained virtually so that if they do make a mistake, no actual harm is caused. The problem is that laying out these digital training scenarios is a laborious and time-consuming task. We could one day just train a deep learning model capable of predicting the consequences of its actions and use that instead.

“We could eventually have an AI that can learn to mimic the rules of driving, the laws of physics, just by watching videos and seeing agents take actions in an environment,” Sanja Fidler, director of NVIDIA’s Toronto research lab, said in a press release. “GameGAN is the first step toward that.” 

NVIDIA’s GameGAN Pac-Man is a fully functional game that both humans and CPUs will be able to play when the company releases it online later this summer.

Amazon Games showed it’s a serious competitor with the new shooter Crucible and has an MMO on the way, but its next game is the one that makes the most sense for Twitch streaming. That’s because Pac-Man Live Studio is not just a variant of the arcade classic, it’s apparently going to be playable directly in its own Twitch channel — perfect for sharing and interaction between streamers and viewers, or just friends teaming up from different locations.

Amazon Games

Tonight’s announcement describes three modes, with an Endless mode that allows you and friends to team up and try to progress through as many levels as you can — as long as one person survives, everyone keeps going. A custom Maze Creator will encourage players to make maps and vote up the most popular ones, and Classic mode lets you take on everyone in the world in a battle to stay atop the leaderboard.