Skip to Content

AI Crushed a Human at Dota 2 (But That Was the Easy Bit)

August 14, 2017

Machine learning software from OpenAI has beaten one of the world’s best players at the video game Dota 2. Elon Musk, who co-founded OpenAI, says that it is the "first ever … defeat [of the] world's best players in competitive e-sports." The Verge reports that Danylo Ishutin, the human player who got beaten, found the AI "a little like [a] human, but a little like something else" to play against.

OpenAI’s software mastered the game, which requires players to defend a base from their opponents, by playing a copy of itself. “We didn’t hard-code in any strategy, we didn’t have it learn from human experts, just from the very beginning, it just keeps playing against a copy of itself,” explains OpenAI researcher Jakub Pachocki in a video. “It starts from complete randomness and then it makes very small improvements, and eventually it’s just pro level.”

It’s an impressive feat, not least because Dota 2 requires making decisions based on imperfect information, unlike games such as Go or chess. But it’s not all good news. Some players have reported that they beat the algorithm after studying its play, and at any rate the AI can only play one-on-one, which is far simpler than regular five-on-five battles that require extensive collaboration. According to TechCrunch, OpenAI says that the five-player game is on its list of problems to crack.

Keep Reading

Most Popular

Geoffrey Hinton tells us why he’s now scared of the tech he helped build

“I have suddenly switched my views on whether these things are going to be more intelligent than us.”

ChatGPT is going to change education, not destroy it

The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better.

Meet the people who use Notion to plan their whole lives

The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.

Learning to code isn’t enough

Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.