In the realm of AI technology, companies have been tirelessly exploring its potential across various domains. Despite the existence of AI bots capable of content writing, image generation, and video editing, there has been a noticeable absence of AI chatbots designed for gaming. However, this may soon change.
Google has recently unveiled its latest project, SIMA – an AI agent undergoing training to play games with the finesse of a seasoned human professional. This groundbreaking development promises to revolutionize gaming experiences by introducing an AI companion capable of rivaling human players.
SIMA, short for Scalable Instructable Multiworld Agent, was introduced by Google through a blog post. This advanced AI agent is equipped with the ability to comprehend natural language instructions and navigate through diverse gaming environments with ease. Leveraging Google DeepMind’s expertise in AI, which has previously showcased remarkable achievements in gaming, from mastering Atari games to conquering StarCraft II, SIMA represents a leap forward in the fusion of AI and gaming.
According to the blog post, video games serve as ideal training platforms for AI systems due to their dynamic and interactive nature. Google emphasizes that SIMA marks a significant milestone in AI development by transitioning from specialized gaming to a more generalized approach. Unlike previous AI agents limited to specific games, SIMA possesses the adaptability to understand and navigate various gaming worlds, executing tasks based on natural-language instructions akin to human players.
This announcement from Google signifies a paradigm shift in the realm of AI-driven gaming. With SIMA poised to challenge human players in their favorite games, gamers can anticipate a new level of competition and engagement. As the boundaries between human and AI capabilities continue to blur, the gaming landscape stands on the brink of an exciting evolution.
“This research marks the first time an agent has demonstrated it can understand a broad range of gaming worlds, and follow natural-language instructions to carry out tasks within them, as a human might,” the company noted.
To train SIMA, Google collaborated with eight game studios and utilised different video games including popular titles like No Man’s Sky and Teardown. Each game presents unique challenges, from navigation to resource management, providing a comprehensive learning experience for the AI.
Unlike previous approaches that focused on single games, SIMA is being trained across multiple environments. Google notes that the AI agent demonstrated remarkable adaptability, performing well even in unseen games, showcasing its potential for generalisation.
SIMA operates through a simple interface, requiring only screen images and natural-language instructions. This accessibility enables it to interact with various virtual environments without needing access to game source code or specialised APIs.
“Our AI agent doesn’t need access to a game’s source code, nor bespoke APIs. It requires just two inputs: the images on screen, and simple, natural-language instructions provided by the user. SIMA uses keyboard and mouse outputs to control the games’ central character to carry out these instructions. This simple interface is what humans use, meaning SIMA can potentially interact with any virtual environment,” the company noted in its post.
The current version of SIMA excels in performing basic tasks across 600 skills, such as navigation and object interaction. Google aims to further enhance SIMA’s capabilities to tackle complex tasks, including strategic planning and multi-step objectives.
A pioneering company dedicated to promoting excellence in education through innovative solutions and platforms. Edu Expo Global Pvt Ltd unites key figures in Education Technology.