game news Video games generated by artificial intelligence, can they work?
Games designed entirely from A to Z by an artificial intelligence, the false good idea?
At the beginning of September, an article published in the Kotaku columns announces the launch of yet another game on the Steam platform. this girl does not exist, only available in English, is offered for a handful of euros, just 3.99. But apart from the article, the communication around the game seems to have failed somewhere; As of this writing, only three users have left ratings on the game page: “Cute Pen Games has a lot of ideas and probably an endless supply of energy to create other productions.”, writes Captain Deatumner. “When you think about all the work that went into making this game, that’s an excellent result.t”, congratulates DDZ. Only a few Fireflies seem disappointed in the experience: “The description makes the game more interesting and deep than it really is.”
The objective of this girl does not exist is putting together puzzle pieces that represent pretty girls while you’re dating them. A concept to say the least summary that we already found in a bunch of other suggestions at the bottom of the page. The illustrations are reminiscent of an old art book by Chinese author Benjamin. But this is not the peculiarity of the title: The developer claims that everything from the art and story to the music and voice acting was generated by some kind of AI.. The idea comes from a couple of developers united under the banner of Cute Pen Games, quite used to classic porn games. And although she may seem like a visionary, no one really takes the bait. The duo transferred the keys to their project to no less than 250 youtubers, and almost none deigned to respond. And despite a catalog full of NSFW content, this girl does not exist it is the studio’s biggest commercial flop. Because despite the ingenuity of the process, it is the creativity part that seems to be missing.
MidJourney, star of AI-generated games
If it’s still in its infancy, no one is really surprised by the concept. Content generated by artificial intelligence is already flooding social networks, especially Twitter. DALL-E, MidJourney… these automated imaging tools need only a simple description to create sometimes amazing images. It is the latter that serves as the basic tool for the game of Cute Pen Game. This summer, another title tasted the magic of AI: Shoon, a small 2D shooter made in just three days by the self-taught “Nao_u”. MidJourney shapes the background, the player’s ship, and the enemies for him. Beforehand, the developer builds the ship models by giving the software text messages related to Star Wars Y armored core. Of course, it takes several tries before you get something really usable. On the other hand, difficult to convince by beautiful prospects; the environments are static, impossible to distinguish the clouds from the vegetation, for example. The AI has other limitations of the same type: the character sprites do not animate. If the presence of stationary spacecraft can circumvent this problem, the concern still narrows the field of possibilities considerably.
But the process is still capable of beautiful feats. In 2018, at the Georgia Institute of Technology, an algorithm designed by doctoral student Matthew Guzdial and associate professor Mark Riedl sucked in hours of footage of people busy playing Super Mario Bros., Kirby’s Adventure, and Mega Man. Then the system machine learning used these sequences as the basis for their own titles. The duo remarkably developed walls of deatha small game with schematic illustrations in which the player tries to escape from a rapidly approaching deadly wall. “It’s the mimicry approach to creativity, which isn’t a bad place to start, because humans also learn to be creative by imitating at first.“, Mr. Riedl will say in the Vice columns. And beyond simple reproduction, the developed AI is also capable of combining the design of various game levels to create new ones. But to really find the right recipe, we first need to know where to relegate AI in the task force.
We don’t know how humans and AI should work together at the design level. The AI could be an assistant, it could be a fill-in-the-blank contractor, it could be a partner, and in the extreme, it could take the lead and the human could be the assistant.
In the big studios, another priority
At big game studios, we still prefer to focus AI research efforts on very specific aspects of a video game experience, which usually translates to NPCs. In May 2021, Sony CEO Kenichiro Yoshida announced a strong collaboration between the company’s AI research division, Sony AI, and PlayStation developers with a view to create intelligent computer controlled characters. The latter would follow a reinforcement learning process whereby an AI learns to act by trial and error and thus would be able to mimic human players. “Leveraging reinforcement learning, we are developing in-game AI agents that can become an adversary or collaborative partner of a player in the game.Yoshida said.
The same year, Electronic Arts states its desire to develop tools capable of using machine learning to reproduce facial expressions and body movements from videos and photos. A system that would exclude the use of actors in a motion capture studio. Even better, it was also planned to use user-generated content so that users could create an avatar by capturing their own silhouette from a smartphone or webcam. At Microsoft, the Cambridge AI research team is leading the Paidia project, which is also investigating the use of reinforcement learning.
The AI of the adversaries is much easier to code than the one of the allies handled by the computer. With the adversary, the relationship is brief. He doesn’t really need to understand what I’m doing, whereas an ally needs to understand what I’m doing, like flanking enemies or taking cover when attacked. This is why we often use commands, which greatly simplify the programming of AI allies. – Journalist Jean Zeid for Polytechnique Insights.
#Video #games #generated #artificial #intelligence #work