DeepMind AI Challenges Pro StarCraft II Players, Wins Almost Every Match

Humans tend to think we’re adept at the games we create, but computers have proven time and time again that we’re just not fast enough to stay on top. Machines have defeated us in chess, Jeopardy!, and even the deviously complex board game Go. Google-owned DeepMind gets credit for that last one, and now it’s dominating another game: StarCraft II. After just 18 months, DeepMind has an AI that beats the world’s best StarCraft II players, and it’s not even close.

DeepMind called its Go-dominating AI “AlphaGo,” and the StarCraft-playing bot got a similar moniker. It’s called AlphaStar, and it has more than 200 years of practice under its belt. Back at Blizzcon in November, DeepMind said its machine learning platform had managed to beat the “Insane” difficulty in-game AI about half the time. Well, it’s gotten much better since then.

AlphaStar is a convolutional neural network. The team started with replays of pro matches, giving AlphaStar a starting point to begin playing the game. Through intensive training with competing models, DeepMind was able to teach AlphaStar how to play the game as well as the best human players. Over time, it whittled the AI down to the five best “agents,” and that’s what it deployed against some of the most skilled StarCraft II players in the world.

The matches actually took place in December, so today’s internet broadcast mostly featured replays of those matches. First, AlphaStar battled a player known as TLO, who primarily plays Zerg in StarCraft. However, he had to play Protoss as that’s the only race AlphaStar trains with right now. This competition wasn’t even close — despite TLO’s best efforts, AlphaStar beat him five games to zero. Next, a different AlphaStar agent went up against a seasoned Protoss player called MaNa. Some of these matches were closer, but AlphaStar still won five games to zero. MaNa also competed against a new AlphaStar agent live on the stream, and this time MaNa finally pulled out a win.

AlphaStar demonstrated impressive micromanagement of units throughout the matches. It was quick to move damaged units back, cycling stronger ones into the front line of battles. AlphaStar also controlled the pace of battle by bringing units forward and dropping back at just the right times to inflict damage while taking less fire itself. This isn’t just a function of brute force actions per minute (APM) — AlphStar has substantially lower APM compared with the human players, but it’s making smarter choices.

The AI also had some interesting strategic quirks. It often rushed units up ramps, which is dangerous in StarCraft II as you can’t see what’s up there until you move in. Still, it somehow worked. AlphaStar also eschewed the tried-and-true tactic of blocking off the base ramp with a wall of buildings. That’s StarCraft 101, but the AI didn’t bother with it and still managed to defend its bases.

It wasn’t until the final live match that the human challenger spotted a flaw in one of the agents. That version of AlphaStar committed to moving almost its entire army as one with the intention of swarming MaNa’s base. However, MaNa was able to repeatedly warp in a few units at the back of AlphaStar’s base. Each time, AlphaStar would turn its army around to deal with the threat. That gave MaNa enough time to build up a more powerful force and take the fight to the AI.

At the end of the day, AlphaStar won 10 matches against pro players and lost just one. If AlphaStar learned from that last match, it might be unbeatable next time.

Continue reading

ARMing for War: New Cortex-A78C Will Challenge x86 in the Laptop Market

ARM took another step towards challenging x86 in its own right with the debut of the Cortex-A78C this week. The new chip packs up to eight "big" CPU cores and up to an 8MB L3 cache.

Blue Origin Challenges NASA Selection of SpaceX for Lunar Lander

The private spaceflight firm founded by Amazon billionaire Jeff Bezos has filed a complaint with the government over the HLS award, claiming its lander design was not given proper consideration.

NASA Robots Compete in DARPA’s Epic Subterranean Challenge Finals

Three years ago, in the misty Before Times of 2018, DARPA launched its Subterranean (SubT) challenge. Now, the final contenders for the $2M grand prize have converged on a former limestone mine in Kentucky, to face the ultimate test of their robots’ skills.

New ‘Collision Chain’ Model Challenges Great Impact Theory

Researchers have published a new "collision chain" model for the Great Impact hypothesis of our rocky inner planets' formation, and it challenges our narrative of how Venus, Earth and the Moon spent their youth.