Google’s DeepMind-fuelled AlphaStar AI is now a StarCraft 2 Grandmaster.
Blizzard’s sci-fi strategy game ultimately proved to be no real match for AlphaStar and, since there are about 100 trillion trillion possible moves in StarCraft 2 at any one time, it’s been no mean feat for the AI, as DeepMind explains in their Nature data:
“Over the course of a decade and numerous competitions, the strongest agents have simplified important aspects of the game, utilised superhuman capabilities, or employed hand-crafted sub-systems. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks. We evaluated our agent, AlphaStar, in the full game of StarCraft 2, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8 percent of officially ranked human players.”
Now, we only understood some of those words, but this feels like a big deal. So what kind of impact could a breakthrough like this have on real life scenarios?
“At DeepMind, we’re interested in understanding the potential – and limitations – of open-ended learning, which enables us to develop robust and flexible agents that can cope with complex, real-world domains,” wrote DeepMind. “Games like StarCraft are an excellent training ground to advance these approaches, as players must use limited information to make dynamic and difficult decisions that have ramifications on multiple levels and timescales.”
DeepMind has always said it will never try to develop tech for ‘lethal autonomous weapons’ so AlphaStar’s achievement should (mmmprobably) not concern us too much.
“To say that this has any kind of military use is saying no more than to say an AI for chess could be used to lead to military applications,” said DeepMind’s Professor David Silver somewhat reassuringly. “Our goal is to try and build general purpose intelligences (but) there are deeper ethical questions which have to be answered by the community.”
The UK’s top StarCraft 2 player, Joshua “RiSky” Hayward, thinks there’s still a lot of work to be done on AlphaStar, despite its new Grandmaster rank.
“It often didn’t make the most efficient, strategic decisions,” he remarked, “but it was very good at executing its strategy and doing lots of things all at once, so it still got to a decent level. When AI got better than people at chess, it did so by making abnormal moves that ended up being stronger than those played by humans. I feel that DeepMind needed more time to create its own innovations and it will be a bit disappointing if the project doesn’t continue.”
Wireframe #25 is out now