Your daily selection of the hottest trending tech news!
According to New on MIT Technology Review (This article and its images were originally posted on New on MIT Technology Review June 25, 2018 at 10:13AM.)
Five different AI algorithms have teamed up to kick human butt in Dota 2, a popular strategy computer game.
Researchers at OpenAI, a non-profit based in California, developed the algorithmic A-team, which they call the OpenAI Five. Each algorithm uses a neural network to learn not only how to play the game, but also how to cooperate with its AI teammates.
This is an important and novel direction for AI, since algorithms typically operate independently. Approaches that help algorithms cooperate with each other could prove important for commercial uses of the technology. AI algorithms could, for instance, team up to out-maneuver opponents in online trading or ad bidding. Collaborative algorithms might also cooperate with humans.
OpenAI previously demonstrated an algorithm capable of competing against top humans at single-player Dota 2. The latest work builds on this using similar algorithms modified to value both individual and team success. The algorithms do not communicate directly, except through game-play.
“What we’ve seen implies that coordination and collaboration can emerge very naturally out of the incentives,” says Greg Brockman, one of the founders of OpenAI, which aims to develop artificial intelligence openly and in a way that benefits humanity. He adds that the team has tried substituting one of the algorithms for a human player, and found this to work very well. “He described himself as feeling very well-supported,” Brockman says.
Dota 2 is a complex strategy game in which teams of five players compete to control a structure within a sprawling landscape. Players have different strengths, weaknesses, and roles, and the game involves collecting items and planning attacks, as well as engaging in real-time combat.
Pitting AI programs against computer games has become a familiar means of measuring progress. DeepMind, a subsidiary of Alphabet, famously developed a program capable of learning to play the notoriously complex and subtle board game Go with superhuman skill. A related program then taught itself from scratch to master both Go and then chess simply by playing against itself.
The strategies required for Dota 2 are more defined than in chess or Go, but the game is still difficult to master. It is also challenging for a machine because it isn’t always possible to see what your opponents are up to, and because teamwork is required.
The OpenAI Five learn by playing against various versions of themselves. Over time, the programs developed strategies much like the ones humans use—including figuring out ways to acquiring gold by “farming” it—as well as adopting a particular strategic role or “lane” within the game.
AI experts say the achievement is significant. “Dota 2 is an extremely complicated game, so even beating strong amateurs is truly impressive,” says Noam Brown, a researcher at CMU in Pittsburgh. “In particular, dealing with hidden information in a game as large as Dota 2 is a major challenge.”
Brown previously worked on an algorithm capable of playing poker, another imperfect-information game, with super-human skill (see “Why poker is a big deal in AI”). If the OpenAI Five team can consistently beat humans, Brown says that would be a major achievement in AI. However, given enough time, he says humans might be able to figure out weaknesses in the AI team’s playing style.
Other games could also push AI further, Brown says. “The next major challenge would be games involving communication, like Diplomacy or Settlers of Catan, where balancing between cooperation and competition are vital to success.
- Got any news, tips or want to contact us directly? Feel free to email us: firstname.lastname@example.org. To see more posts like this please subscribe to our newsletter by entering your email. By subscribing you’ll receive the top trending news delivered to your inbox.
This article and images were originally posted on [New on MIT Technology Review] June 25, 2018 at 10:13AM. Credit to Author Will Knight and New on MIT Technology Review | ESIST.T>G>S Recommended Articles Of The Day.