[ad_1]
Google DeepMind on Wednesday unveiled a unique artificial intelligence (AI) model that can play 3D video games like a human would. The AI model is called Scalable Instructable Multiworld Agent or SIMA, and it involves learning to interact with various game environments and perform different tasks. The model is currently under research and is still being trained to gain experience performing more complex movements. Google says that once perfected, the AI model can have a wide range of use cases both in the real world and online.
in a blog entry, DeepMind’s SIMA team explained that the AI model is not being developed to be a super intelligent player that can beat any game. Instead, the goal is to teach you how to move around 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 it is a significantly difficult task and that it should be a focus of attention.
“This is an important goal for AI in general, because while large language models have given rise to powerful systems that can capture knowledge about the world and generate plans, they currently lack the ability to take actions on our behalf,” stated the SIMA team. .
Tasks performed by the SIMA AI model
Photo credit: Google DeepMind
To create a learning environment for the AI model, Google DeepMind partnered with eight gaming studios and trained SIMA on nine different video games. Some of them include No Man’s Sky from Hello Games, Teardown from Tuxedo Labs, Goat Simulator 3 and Valheim from Coffee Stain Studios, and more. The AI model was exposed to new interactive worlds in each game and had to learn how to navigate the world, interact with objects, use menus, and more.
The company also created four research environments, including a new environment built with Unity called Construction Lab. In this particular environment, the AI model was tasked with building sculptures from building blocks to test its manipulation of objects and your intuitive understanding of the physical world.
Google highlighted that the current version of SIMA was assessed on 600 basic skills, including navigation such as turning left and driving a car, interacting with objects such as climbing a ladder and making a helmet, and more. The tasks were largely simple and could be completed in 10 seconds.
According to the company, training an AI model on a diverse set of 3D video games where it follows human instructions and acts accordingly can have a big impact in the future. The company is now focused on training SIMA with more complex instructions “that require high-level strategic planning and multiple subtasks to complete, such as finding resources and building a camp.” Google hints that these tasks can be translated into the real world, and the company is working to find ways they can be useful to humans.