Google is training Gemini-powered agents using Goat Simulator 3
Google DeepMind has unveiled its latest innovation in artificial intelligence with the introduction of SIMA 2, a Gemini-powered agent designed to navigate the whimsical world of video games, including the quirky Goat Simulator 3. This new AI agent, which stands for “scalable instructable multiworld agent,” is an evolution of the original SIMA project aimed at enhancing the gaming experience by serving as a companion for human players. As reported by MIT Technology Review, SIMA 2 is not just a passive player; it actively learns and adapts to the complexities of open-ended games, which is a significant leap forward in AI gaming technology.
The development of SIMA 2 reflects a broader trend in AI research, where games are increasingly utilized as a testing ground for advanced algorithms and machine learning techniques. As noted by Joe Marino, a researcher at Google DeepMind, gaming environments provide a rich framework for agents to learn and evolve. This is particularly evident in games like Goat Simulator 3, where the unpredictable and humorous nature of the gameplay allows the AI to explore a variety of scenarios and challenges. Moreover, human players can interact with and guide the agent, facilitating a collaborative gaming experience that enhances both the player’s enjoyment and the agent’s learning curve.
The implications of SIMA 2 extend beyond mere entertainment; they raise important questions about the future of AI in gaming and its potential impact on player engagement. As AI companions become more sophisticated, they could fundamentally alter how we experience video games, blending the lines between player and AI. While the introduction of AI-driven agents like SIMA 2 promises to enrich the gaming landscape, it also invites scrutiny regarding the ethical considerations of AI in interactive environments. As this technology evolves, it will be crucial to monitor its effects on gameplay dynamics and the broader gaming community.
Google has developed an AI-powered agent that’s playing video games, including
Goat Simulator 3
— yes, a goat-based video game.
Google DeepMind created a Gemini-powered agent called SIMA 2 — “scalable instructable multiworld agent” — that’s navigating the world of
Goat Simulator 3
,
reported
MIT Technology Review
.
The AI agent is called SIMA 2 because, well, there was an original SIMA. We
covered the original project at Mashable
. The agent was designed to essentially serve as a video game companion — an AI-powered player that could accompany human players. (The
ROG Xbox Ally X gaming handheld
has a similar, Copilot-powered feature.) SIMA 2 is apparently an improved version of the original.
SEE ALSO:
Google is training an AI to play video games — why this could be problematic
“Games have been a driving force behind agent research for quite a while,” Joe Marino, a researcher at Google DeepMind, said this week, via
MIT Technology Review
.
The idea behind SIMA 2 is that the agent can learn and adapt in open-ended, complicated video games. A human player can also help direct the agent and improve its performance.
