From Atari to Go to StarCraft, games have driven some of the biggest breakthroughs in AI. Now, we’re partnering with game developers to prototype new gameplay experiences that push the frontiers of both gaming and AI.
Since DeepMind’s foundation in 2010, the constrained yet rich worlds of games have played a critical role in understanding intelligence. They have driven some of our biggest AI breakthroughs, from mastering Atari to helping solve protein structure prediction - and they are still at the heart of what we do.
Gaming is in GDM’s DNA. Demis Hassabis, one of Google DeepMind's founders, is himself a former game developer, as are many of us in the GDM team. Together, we have decades of hands-on experience in game development and a deep respect for the craft of making games.
We’ve always been clear that doing AI research with games requires deep partnership with game developers - like our major new research partnership with Fenris Creations and the EVE Universe that we unveiled earlier this year, and the work we’ve done together with acclaimed studios like Hello Games, Coffee Stain Studios, Foulball Hangover and others.
Games as the engine of AI research
Our journey began when a small team trained a deep neural network to play Atari 2600 games directly from raw pixels. The Deep Q-Network (DQN) learned to play 49 different games — from Pong to Breakout to Space Invaders — without any game-specific engineering. The 2015 Nature paper on DQN helped catalyze the modern era of deep reinforcement learning.
From there, we attempted to master more complex games, with each milestone producing more capable and general systems. AlphaGo defeated world champion Go player Lee Sae Dol in 2016 — a feat many experts thought was still a decade away. AlphaGo Zero surpassed every previous version by learning entirely from self-play, with no human data at all. AlphaZero generalized this approach to master chess, shogi, and Go with one algorithm, while MuZero learned to play without even knowing the rules. In 2019, AlphaStar reached Grandmaster level in StarCraft II, navigating real-time complexity and imperfect information.
For each game, AI enriched the playing experience. AlphaGo's famous Move 37 was a play so unexpected that professional commentators initially thought it was a mistake, overturning centuries of received wisdom in Go and inspiring experts to explore new strategies. AlphaZero similarly inspired entirely new lines of play in chess. Crucially, the spirit of exploration that succeeded in games had profound impacts for other AI systems: AlphaFold applied these foundations to help solve the 50-year grand challenge of protein structure prediction, a breakthrough which was recognized with the 2024 Nobel Prize in Chemistry.
From mastering games to understanding them
Our earlier work demonstrated that AI could master any game given a clear objective and enough training. But the real world doesn't come with scores and rule books — which led us to ask a fundamentally different question: can AI understand and interact with any game world the way a person would?
This is the challenge behind SIMA, our Scalable Instructable Multiworld Agent. Rather than optimizing for a high score, SIMA is a generalist agent that ‘sees’ what a player would see on screen, understands natural language instructions, and acts through ordinary keyboard and mouse controls — requiring no APIs or source code access.
Powered by Gemini, our frontier AI models, SIMA 2 acts as an interactive companion capable of real-time reasoning and conversation. It achieves human-like play across complex 3D research environments and video games including No Man's Sky, Valheim, Hydroneer, and more.
For game developers, a truly general gaming agent would unlock AI capabilities that work with existing games — no modifications to the game code required. This could power entirely new gameplay, from AI companions that genuinely understand the game world to Non-Player Characters (NPCs) that adapt and respond in ways that scripted systems never could.
A general gaming agent could also transform how games are made. During development, when the game changes with every commit, such agents could enable truly robust QA testing. Post-launch, when new content is introduced or players behave unpredictably, they could adapt in real time — generalising to new situations without needing to be re-scripted.
To develop SIMA agents safely and responsibly, we've partnered with acclaimed game studios and we are building a growing portfolio of games for AI research. This allows us to challenge our agents with ever more complex tasks that may one day transfer to solving problems in the real world.
Exploring new frontiers of AI and games research, in partnership with game developers
Game studios bring expert craft, extraordinary game worlds, and deep knowledge of their players. We bring frontier AI — from Gemini to research in generative interactive environments and embodied agents — research expertise, and our team’s unique game development background and years of experience building AI for interactive environments. Together, we focus on discovering breakthrough experiences — never-before-seen gameplay that wouldn't be possible without AI.
It's not about the tech, it's about fun experiences. So we take a ‘show, don't tell’ approach with our partners. Our team works hand in hand with game developers, exploring new ideas and building playable prototypes to find the fun.
Our latest research partnership with Fenris Creations, the independent studio behind the EVE Universe, represents a new chapter in our history of AI research in games.
Fenris Creations has spent more than two decades building one of the most extraordinary persistent worlds in gaming. EVE Online, launched in 2003, is a massively multiplayer space simulation where thousands of players share a single universe that has evolved continuously for more than 20 years. Its player-driven economy features real supply-and-demand dynamics and trade networks spanning thousands of star systems. Its landscape — shaped by alliances, conflicts and diplomacy — is driven by human interaction.
For AI research, this is a golden opportunity. It's a living, evolving world that demands precisely the capabilities we believe are essential for frontier AI:
- Continual learning: Acquiring new skills without forgetting what came before, in a constantly changing world.
- Memory: Accumulating and retrieving knowledge across timescales that extend far beyond today's model context windows.
- Long-horizon planning: Reasoning over weeks, months, or even years.
- Complex multi-agent dynamics: Navigating cooperation, competition, negotiation, economics, and emergent social behavior at scale.
These challenges sit at the core of our broader research initiative to create systems that learn continuously from experience, with the rate of learning accelerating over time. We believe these frontier capabilities could unlock new gameplay experiences in the future.
Our research partnership extends across Fenris Creations' expanding universe, offering distinct environments for AI development. While EVE Online offers a large-scale single-shard persistent universe, EVE Vanguard is played from a first-person perspective, bringing ground-level, fast-paced tactical decision-making to the broader persistent world. This creates opportunities to study agents operating across multiple levels of abstraction, from twitch-level tactics to galaxy-spanning strategy.
Furthermore, EVE Frontier — with its programmable "Smart Assemblies” and its open, extensible architecture — offers an open-ended environment where the very rules of the world can change, demanding agents that adapt to entirely new game mechanics.
Our collaboration has already delivered real player value: the Aura Guidance system uses Gemini to deliver player-generated knowledge, based on real Rookie Help questions and answers, to help new pilots.
Our longer-term research program begins with an offline instance of EVE Online, which is a safe sandbox, separate from live players. It then progresses through EVE Frontier as a space to study how humans and agents can coexist in a persistent and open-ended world. Only when capabilities are mature would we consider bringing them to EVE Online and EVE Vanguard with the aim of enriching human play.
The road ahead
Games have always been a mirror for intelligence. As they become more complex, more persistent, and more open-ended, so do the AI systems we build to navigate them.
We are aiming for the same ultimate goal we always have: AI as a catalyst, not a replacement. Our long-term ambition is to unlock breakthrough gameplay experiences, make games more accessible and more personalized, and — as we've seen from AlphaGo to AlphaFold — apply what we learn in games to problems in the real-world and to advance scientific discovery.
We're grateful to all of our game partners on this journey, and to Fenris Creations for joining us on this next chapter. We can't wait to share what we discover.
Acknowledgements
We’d like to recognize the many teams across Google DeepMind for their contributions over the years to advancing AI research safely and responsibly in games.
Special thanks to all of the game developers who partnered with us: Coffee Stain (Valheim, Satisfactory, Goat Simulator 3), Fenris Creations (EVE Online, EVE Vanguard, EVE Frontier), Foulball Hangover (Hydroneer), Hello Games (No Man's Sky), Keen Software House (Space Engineers), RubberbandGames (Wobbly Life), Strange Loop Games (Eco), Thunderful Games (ASKA, The Gunk, Steamworld Build), Digixart (Road 96), and Tuxedo Labs & Saber Interactive (Teardown).
Facts Only
* DeepMind's foundation began in 2010.
* A team trained a deep neural network to play Atari 2600 games from raw pixels, leading to the Deep Q-Network (DQN).
* AlphaGo defeated world champion Go player Lee Sae Dol in 2016.
* AlphaGo Zero learned entirely from self-play without human data.
* AlphaZero mastered chess, shogi, and Go with one algorithm.
* AlphaStar reached Grandmaster level in StarCraft II in 2019.
* AlphaFold applied AI foundations to protein structure prediction.
* SIMA is a Scalable Instructable Multiworld Agent designed to understand game worlds and act via keyboard/mouse controls without API access.
* SIMA 2 uses Gemini and acts as an interactive companion in environments like No Man's Sky and Valheim.
* The research partnership involves Fenris Creations and the EVE Universe.
* EVE Online launched in 2003.
* Research focuses on continual learning, memory, long-horizon planning, and complex multi-agent dynamics within persistent worlds like EVE Frontier.
Executive Summary
The development of AI in games is rooted in the long history of using games to advance artificial intelligence research, starting with training deep neural networks to play Atari games and progressing through milestones like AlphaGo and AlphaStar. This evolution demonstrates how gaming environments served as critical engines for breakthroughs in deep reinforcement learning and general intelligence. The current focus shifts toward creating general gaming agents, such as SIMA, capable of understanding game worlds and interacting with them via natural language, rather than just optimizing for scores. This research requires deep partnership with game developers to explore novel gameplay experiences and build agent capabilities that can translate into new forms of interaction within existing and future games.
The partnership with Fenris Creations and the EVE Universe provides a unique testing ground due to its persistent, evolving nature, which demands advanced AI capabilities like continual learning, long-horizon planning, and complex multi-agent dynamics. The ultimate goal is to use these advances not just for gaming, but to unlock generalized intelligence capable of solving real-world problems, building on prior successes like AlphaFold.
Full Take
The narrative constructs a powerful trajectory: games as foundational training grounds for general intelligence, culminating in agents capable of generalized world understanding. The transition from mastering specific game mechanics (Atari) to building holistic understanding of simulated reality (EVE Online) sets up an implicit argument that complexity demands embodied interaction. The central tension lies between the pursuit of "fun experiences" and the rigor required for frontier AI research; the text attempts to bridge this by positioning games as a necessary, engaging methodology rather than just a sandbox.
The focus on EVE Online highlights a shift in what constitutes valuable experiential data: moving from score-based optimization to dynamic, persistent social and economic modeling. This suggests that future AI breakthroughs may depend less on discrete tasks and more on systems capable of managing emergent complexity over long timescales. The implication is that truly advanced AI must grapple with non-deterministic, evolving systems—like a living game world—to develop the memory and planning skills necessary for real-world generalization. The risk here is framing the pursuit of agent capability as inherently tied to the experience itself, potentially overlooking the purely mathematical or architectural breakthroughs that drive these results.
The move toward general agents like SIMA suggests an aspiration to decouple intelligence from specific game APIs, aiming for a universal understanding of interactive environments. This mirrors the ambition in AlphaFold—applying learned principles across domains. The pattern observed is the leveraging of emergent complexity (games) to force cognitive capabilities (planning, memory). The implicit assumption is that these emergent properties are universally applicable. The question remains whether the specific dynamics of a space simulation like EVE Online impose unique, non-transferable constraints or lessons on learning that might narrow the scope of general agents if generalization is pursued too aggressively without sufficient grounding in the game-specific context. What empirical evidence exists for transferring multi-agent social reasoning from an MMO environment to novel real-world planning scenarios?
Sentinel — Human
The text exhibits a high degree of structured argumentation typical of corporate/research press releases but maintains enough contextual depth and strategic framing to suggest careful human authorship guiding an AI-centric narrative.