Wednesday, 2 April 2025
29.1 C
Singapore
35.6 C
Thailand
22.1 C
Indonesia
28.5 C
Philippines

Meet your new co-op buddy: Google DeepMind’s game-playing AI

Discover how Google DeepMind's SIMA, a video game-playing AI, aims to transform gaming by acting as a cooperative companion.

Imagine having a gaming companion who’s good at playing various 3D video games and responds to your verbal instructions with the eagerness of a human teammate. Google DeepMind has taken a significant leap towards this future with their latest innovation, SIMA (Scalable Instructable Multiworld Agent), an AI designed to play multiple video games and act upon your commands, pushing the boundaries of traditional game-playing AI models.

A leap beyond conventional game AI

Unlike traditional AI characters in games, which operate within predefined rules and commands, SIMA has no direct access to the game’s code or mechanics. Instead, it learns from observing hours of human gameplay across different games. This observation includes the actions taken and verbal instructions shared between players, providing a rich dataset from which the AI can understand and replicate human-like gameplay.

For example, SIMA can learn that moving pixels in a specific pattern equates to “moving forward” or that interacting with an object resembling a doorknob results in a door opening. This approach allows it to understand and perform actions more nuanced than the binary outcomes of winning or losing, typical of most game AI.

Bridging games and the real world

The training for SIMA wasn’t limited to one game. Instead, it encompassed a variety of titles, from “Valheim” to “Goat Simulator 3”, with the cooperation of their developers. This diversity in training aimed to equip the AI with the ability to generalise its learning to games it has never encountered before, a concept known as generalisation in AI research. While the AI performed better on unfamiliar games than those trained on single titles, each game’s unique mechanics and terminologies still pose a challenge, highlighting the need for extensive and varied training data.

One of the project’s leads, Tim Harley, emphasised the goal of creating a game-playing companion that feels more natural and less rigid than the AI characters we’re accustomed to. By observing and learning from human gameplay, SIMA is designed to adapt and respond in ways more aligned with how humans play and interact with games.

Beyond gaming: The future of AI companions

This approach to training AI opens up new possibilities beyond gaming. Traditional AI training methods like reinforcement learning rely on clear reward signals like scores or win/loss outcomes. However, using imitation learning from human behaviour, SIMA is trained to pursue objectives based on textual goals. This allows for a broader range of actions and interactions that more closely mimic human decision-making.

The potential for AI agents like SIMA extends into other domains where open-ended collaboration and creativity are valued. From enhancing NPC interactions in games to simulating complex behaviours, the technology behind SIMA represents a step towards more versatile and human-like AI companions.

As we look towards a future where AI can serve as a cooperative companion in various tasks, the work by Google DeepMind’s researchers on SIMA offers a glimpse into the exciting possibilities of blending AI technology with human-like intuition and adaptability.

Hot this week

Uwant D500 Pro Wet and Dry Vacuum Cleaner review: Designed for comfort and ease of use

The Uwant D500 Pro Wet and Dry Vacuum Cleaner offers powerful suction, real-time sterilisation, and ergonomic design for effortless cleaning. With self-cleaning, AI-powered drying, and intuitive controls, it ensures a seamless, low-maintenance experience for modern homes.

POCO launches F7 Series in Singapore with high performance and affordability

POCO launches F7 Ultra and F7 Pro in Singapore, offering flagship features, strong performance, and early bird gifts from 27 March.

Android Auto beta now supports full-screen gaming

Android Autoโ€™s latest beta introduces full-screen gaming, allowing you to play Candy Crush Soda Saga and Angry Birds 2 while parked.

ESET uncovers RansomHub links to rival gangs and highlights emerging EDR killer threats

ESET uncovers RansomHubโ€™s links to rival gangs and reveals its custom EDR killer, signalling new threats in the ransomware landscape.

OpenAI pauses free GPT-4o image generation after viral Studio Ghibli trend

OpenAI halts free GPT-4o image generation after viral Studio Ghibli trend raises legal concerns, leaving paid users with continued access.

Zelle is removing its stand-alone app

Zelle is shutting down its stand-alone app, but you can still use the service through your bankโ€™s app. Hereโ€™s what you need to know.

Apple may launch an AI-powered Health app with a coaching feature next year

Apple may introduce an AI-powered Health app with coaching, food tracking, and fitness guidance in 2026, possibly as a new subscription service.

These robot vacuums are getting smarter with Apple Home support

Appleโ€™s iOS 18.4 update adds Matter support for robot vacuums, enabling control via Apple Home. Roborock, iRobot, and Ecovacs are updating their devices.

Gmail introduces easier encryption for business emails

Google introduces a new encryption model for Gmail, making it easier for businesses to send secure emails without special software or certificates.

Related Articles