38 Posts

Game Makers Embrace Generative AI: How Nvidia, Blizzard, and more are using AI in video games.

Game Makers Embrace Generative AI: How Nvidia, Blizzard, and more are using AI in video games.

The next generation of video games could be filled with AI-generated text, speech, characters, and background art. Nvidia announced a system that enables players to converse directly with in-game characters. Meanwhile, game developers are using generative AI to produce media assets.
Transformer-based system simulating simulate the Atari game "Pong"

Efficient Reinforcement Learning: IRIS used reinforcement learning to master Atari games with little gameplay.

Both transformers and reinforcement learning models are notoriously data-hungry. They may be less so when they work together. Vincent Micheli and colleagues at the University of Geneva trained a transformer-based system to simulate Atari games using a small amount of gameplay.
Scene from a video game called Rocket League

AI Cheat Bedevils Popular Esport: Gamers are using AI to cheat in Rocket League.

Reinforcement learning is powering a new generation of video game cheaters. Players of Rocket League, a video game that ranks among the world’s most popular esports, are getting trounced by cheaters who use AI models originally developed to train contestants.
Model that defeats KataGo, an open source Go-playing system

Champion Model Is No Go: Adversarial AI Beats Master KataGo Algorithm

A new algorithm defeated a championship-winning Go model using moves that even a middling human player could counter. Researchers trained a model to defeat KataGo, an open source Go-playing system that has beaten top human players.
Gato’s performance on simulated control tasks | Image captions generated by Gato

One Model, Hundreds of Tasks: Multimodal Transformer Performs Over 600 Different Tasks

Researchers took a step toward achieving a longstanding goal: One model that performs a whole lot of very different tasks. Scott Reed, Konrad Żołna, Emilio Parisotto and a team at DeepMind announced Gato.
Deck of playing cards

Bridge to Explainable AI: AI System Outplays Human Bridge Champions

DeepMind’s AlphaGo famously dominated Go, a game in which players can see the state of play at all times. A new AI system demonstrated similar mastery of bridge, in which crucial information remains hidden.
ZooBuilder videoscreen capture

Animal Animations From Video: ZooBuilder AI Tool Converts Animal Videos into Animations'

A video game studio is looking to machine learning to cut the effort and expense of populating three-dimensional scenes with animated animals.
Gran Turismo Sport race

Fast and Daring Wins the Race: GT Sophy AI model beats humans at Gran Turismo Sport.

Armchair speed demons have a new nemesis. Peter Wurman and a team at Sony developed Gran Turismo Sophy (GT Sophy), a reinforcement learning model that defeated human champions of Gran Turismo Sport, a PlayStation game that simulates auto races right down to tire friction and air resistance.
A chorus of reindeers singing carols from a Reindeer Holiday Songbook on a snowy night

Voices for the Voiceless: Generative AI models are creating voices for Hollywood and video games.

Musicians and filmmakers adopted AI as a standard part of the audio-production toolbox. What happened: Professional media makers embraced neural networks that generate new sounds and modify old ones. Voice actors bristled.
Sequence of famous arcade games' scenes

Solve RL With This One Weird Trick: How to get better performance from reinforcement learning.

The previous state-of-the-art model for playing vintage Atari games took advantage of a number of advances in reinforcement learning (RL). The new champion is a basic RL architecture plus a trick borrowed from image generation.
Video showing AI working on a video-game to blast virtual enemies at superhuman speed

Fake Aim: Gamers cheat with AI-powered aim assist.

Gamers looking to cheat in first-person shooters can’t miss with AI-assisted marksmanship. A video-game hack uses computer vision to blast virtual enemies at superhuman speed, Ars Technica reported.
Automated player learning by watching recorded gameplay

Behavioral Cloning Shootout: AI learns to play Counter Strike Global Offensive.

Neural networks have learned to play video games like Dota 2 via reinforcement learning by playing for the equivalent of thousands of years (compressed into far less time). In new work, an automated player learned not by playing for millennia but by watching a few days’ worth of recorded gameplay.
Crossword solving during a major puzzle competition

Crosswords Go the Way of Go: An AI system beat 1,300 humans at a crossword puzzle contest.

A hybrid of deep learning and symbolic AI took the prize at a major puzzle competition. A system called Dr. Fill outscored nearly 1,300 human contestants at April’s annual American Crossword Puzzle Tournament.
Process showing how FastNeRF accelerates the photorealistic 3D rendering method

Virtual Reality in Real Time: FastNeRF renders 3D scenes at 200 frames per second.

Ideally, real-time 3D applications such as virtual and augmented reality transition smoothly between different viewpoints of a scene — but generating a fresh perspective can take time. New research speeds the process.
Minecraft video capture

3D Object Factory: Researchers train neural networks to build in Minecraft.

In the open-ended video game Minecraft, players extract blocks of virtual materials from a 3D environment to assemble objects of their own design, from trees to cathedrals. Researchers trained neural networks to generate these structures.
Load More

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox