Skip to Content
Uncategorized

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.

Deep Dive

Uncategorized

Embracing CX in the metaverse

More than just meeting customers where they are, the metaverse offers opportunities to transform customer experience.

Identity protection is key to metaverse innovation

As immersive experiences in the metaverse become more sophisticated, so does the threat landscape.

The modern enterprise imaging and data value chain

For both patients and providers, intelligent, interoperable, and open workflow solutions will make all the difference.

Scientists have created synthetic mouse embryos with developed brains

The stem-cell-derived embryos could shed new light on the earliest stages of human pregnancy.

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 customer-service@technologyreview.com with a list of newsletters you’d like to receive.