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.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

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.