Google's AI Is Getting Really Good at Minecraft — Without Being Trained on the Game "A Minecraft Movie" led the domestic box office this weekend and the game is as popular as ever — and not only with humans.

By Sherin Shibu Edited by Melissa Malamut

Key Takeaways

  • Google’s DeepMind research team created a new AI system called Dreamer.
  • Dreamer found out how to collect diamonds in Minecraft without prior knowledge of the game — just as fast as a skilled player.

"A Minecraft Movie" led the domestic box office last weekend with $163 million in ticket sales, and the film set the record for the highest-opening video game adaption.

The Warner Bros.' and Legendary Entertainment film, starring Jack Black, Jason Momoa, and Jennifer Coolidge, adapts the mega-popular video game into a live-action (and CGI) feature.

Minecraft, which has sold more than 300 million copies, asks its more than 200 million monthly active players to navigate a virtual world full of different environments, like forests and deserts. Players use the resources at their disposal, like wood from trees, for example, to build objects and mine prized items like diamonds, which are the source of the best weapons and armor in Minecraft.

Minecraft was released in 2009 and the mobile version of the game generated revenues of over $98 million in 2024 alone. The average age of a Minecraft player is 24.

And while the movie's success shows that the game is more popular than ever, longtime players and fans can expect some new competition: Google's AI can now play Minecraft, and accomplish a multi-step task, without being trained, in the same amount of time as a skilled human player.

How Google's 'Dreamer' Plays Minecraft

A study published last week in the scientific journal Nature shows that an AI system called Dreamer, which was developed by Google's San Francisco-based DeepMind team, figured out (on its own) how to accomplish the difficult Minecraft task of collecting diamonds — a first for AI.

"Dreamer marks a significant step towards general AI systems," Google DeepMind researcher and study co-author Danijar Hafner told Nature. "Every time you play Minecraft, it's a new, randomly generated world."

Related: Gamers Spent 16.7 Billion Hours on Roblox in Just 3 Months. Here's What Roblox Is and Why Your Kids Won't Stop Playing It

Dreamer played Minecraft for nine days straight, with Google researchers resetting the universe every 30 minutes so that the AI had to constantly adjust to a new world.

Collecting a diamond in Minecraft is no easy feat: Users have to find trees, cut them down, build a crafting table, build a wooden pickaxe, and dig deep underground to find a diamond. It can take a human player 20 to 30 minutes to first mine a diamond.

After nine days, Dreamer was able to learn enough about Minecraft to mine a diamond in less than 30 minutes, just as quickly as a human player.

Throughout the experiment, Dreamer was able to absorb its physical environment in Minecraft and improve at the game without receiving step-by-step instructions from a human on how to get better. Previous research trained AI to play Minecraft by exposing it to hours of videos of players; Dreamer had no such prior training before it was introduced to the game.

"Dreamer is, to our knowledge, the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula," the Google researchers claimed in the study.

Related: Hasbro's CEO Saw a 'Clear Signal' That It Was Time to Embrace AI for Dungeons & Dragons

Instead of watching videos, Dreamer used a technique called "reinforcement learning" to get better at Minecraft. The trial-and-error technique means that the AI identified actions that received rewards and repeated them while discarding other actions that failed to produce rewards.

Dreamer was also able to mine diamonds quickly by creating a mental model of its Minecraft surroundings, a model that grew more detailed each time it played, and mentally testing scenarios without actually running through them.

Hafner told Nature that Dreamer had "the ability to imagine the future" and suggested that this mental testing capability could one day help develop robots that interact more intelligently with the real world.

Sherin Shibu

Entrepreneur Staff

News Reporter

Sherin Shibu is a business news reporter at Entrepreneur.com. She previously worked for PCMag, Business Insider, The Messenger, and ZDNET as a reporter and copyeditor. Her areas of coverage encompass tech, business, strategy, finance, and even space. She is a Columbia University graduate.

Want to be an Entrepreneur Leadership Network contributor? Apply now to join.

Buying / Investing in Business

Big Investors Are Betting on This 'Unlisted' Stock

You can join them as an early-stage investor as this company disrupts a $1.3T market.

Buying / Investing in Business

From a $120M Acquisition to a $1.3T Market

Co-ownership is creating big opportunities for entrepreneurs.

Business Ideas

70 Small Business Ideas to Start in 2025

We put together a list of the best, most profitable small business ideas for entrepreneurs to pursue in 2025.

Business News

AI Could Cause 99% of All Workers to Be Unemployed in the Next Five Years, Says Computer Science Professor

Professor Roman Yampolskiy predicted that artificial general intelligence would be developed and used by 2030, leading to mass automation.

Business News

You Can Get Paid $18,000 More a Year By Adding AI Skills to Your Resume, According to a New Study

Employers are emphasizing AI skills — and are willing to pay a lot more if you have them.