Google DeepMind’s SIMA Is an AI Agent That Can Play 3D Video Games

Mar14,2024


Google DeepMind on Wednesday introduced a unique artificial intelligence (AI) model that can play 3D video games just like a human. The AI ​​model is called Scalable Instructional Multiworld Agent, or SIMA, and it is learning how to interact with different gaming environments and complete different tasks. The model is currently in research and is still being trained to build expertise in performing more complex activities. Google says that once perfected, the AI ​​models could have a wide range of use cases both online and in the real world.

In a blog post, DeepMind's SIMA team explained that the AI ​​model is not being developed to be a super-intelligent gamer that can beat any game. Instead, the aim is to teach it how to move around in a 3D game in open-world situations and understand how a human would react and interact with it using natural language instructions. Google highlights that this is quite a difficult task and should be focused on.

The SIMA team said, “This is an important goal for AI in general, because large language models have given rise to powerful systems that can acquire knowledge about the world and formulate plans, but currently they lack There is a lack of ability to act on our part.” ,

Google Sima1 Google DeepMind Sima

Tasks performed by AI model Sima
Photo Credit: Google DeepMind

To create a learning environment for the AI ​​model, Google DeepMind partnered with eight game studios and trained SIMA on nine different video games. Some of them include No Man's Sky by Hello Games, Teardown by Tuxedo Labs, Goat Simulator 3 and Valheim by Coffee Stain Studios, and more. The AI ​​model was exposed to new interactive worlds in each game and had to learn how to navigate through the world, interact with objects, use menus, and more.

The company also created four research environments, including a new environment called Construction Lab built with Unity. In this special environment, the AI ​​model was tasked with creating sculptures from building blocks to test its object manipulation and intuitive understanding of the physical world.

Google highlighted that the current version of SIMA was assessed across 600 basic skills, including navigation like turning left and driving a car, object interactions like climbing stairs and putting on a helmet, and more. The tasks were largely simple and could be completed within 10 seconds.

According to the company, training the AI ​​model on a diverse set of 3D video games, where it follows human instructions and acts accordingly, could have a big impact in the future. The company is now focusing on training SIMA with more complex instructions “that require high-level strategic planning and multiple sub-tasks to complete, such as finding resources and building a camp.” Google hints that these functions may translate to the real world and that the company is working on finding ways that could be helpful to humans.


Affiliate links may be automatically generated – see our ethics statement for details.

Related Post

Leave a Reply

Your email address will not be published. Required fields are marked *