Google and Blizzard invite you to train AI with 'StarCraft II'

Isaac Cain
August 10, 2017

Starcraft II has been a target for Alphabet's DeepMind AI research for a while now - the UK AI company took on Blizzard's sci-fi strategy game starting past year, and announced plans to create an open AI research environment based on the game to make it possible for others to contribute to the effort of creating a virtual agent who can best the top human StarCraft players in the world.

"We've learned a lot during our collaboration with DeepMind on this project, and we're very excited to get these tools in your hands to see what fantastic things we can create together", Blizzard wrote in a separate blog post also published Wednesday.Among the tools Activision Blizzard is making public are a dataset of anonymized game replays - essentially recordings of humans playing the game - that computer scientist will be able to use to help train their systems.

"That is why we, along with our partner Blizzard Entertainment, are excited to announce the release of SC2LE, a set of tools that we hope will accelerate AI research in the real-time strategy game StarCraft II". Blizzard and DeepMind have released a joint paper that outlines the environment and reports baseline results in the mini-games inside the toolkit. The original StarCraft is used by AI and machine learning researchers in the annual AIIDE bot competition. To succeed, a player needs to have a good memory, prioritize among tasks, and plan under conditions of uncertainty. The main goal is certainly to win the game, but to accomplish this goal, the AI has to manage sub-goals like finding resources, building units, and more.

Because of these factors, StarCraft II comes much closer to approximating many real-world situations than games such as chess, Go or even Poker. The two companies unveiled that interface, along with a set of tools to help other computer scientists train AI agents to play the game, at a machine learning conference in Australia Thursday.

More news: Swiss franc surges as Korea tensions rise

The game also has other qualities that appeal to researchers, such as the large pool of avid players that compete online every day.

DeepMind had announced in November that it would be using StarCraft II as a testing platform for AI and machine-learning research, opening the environment worldwide.

"Ultimately, agents will play directly from pixels, so to get us there, we've developed a new image-based interface that outputs a simplified low-resolution RGB image data for map and minimap, and the option to break out features into separate "layers", like terrain heightfield, unit type, unit health, etc".

But with this new API, researchers can program learning algorithms and then run hundreds, thousands, or even millions of StarCraft II games to give the A.I. the data it needs to spot hard trends.

Other reports by LeisureTravelAid

Discuss This Article

FOLLOW OUR NEWSPAPER