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

Bruno Cirelli
Agosto 10, 2017

But so far, space is proving a hard frontier for the company's algorithms. "But when it comes to the full game, even strong baseline agents, such as A3C, can not win a single game against even the easiest built-in AI", DeepMind said in its blog post.

A machine-learning API that Blizzard developed to give developers an easy way to hook into the game.

The company said new breakthroughs in machine learning would be required for its software agents to master the game.Just how close DeepMind may be to such breakthroughs, the blog post didn't reveal. Since then DeepMind has published a number of research papers that hint it may be closing in on creating software capable of numerous tasks - such as prioritizing goals, long-term planning, and memory - that any system will need in order to play StarCraft II successfully. 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. The original game is also already used by AI and ML researchers, who compete annually in the AIIDE bot competition. This means that the AI is not able to see the entire map or move within the map with as much swiftness as an agent can actually do. Part of StarCraft's longevity is down to the rich, multi-layered gameplay, which also makes it an ideal environment for AI research.

The set of tools released by DeepMind include several elements from the game that can help in development of artificial intelligence.

"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 unbelievable 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. DeepMind says that meeting that mission requires it to design agents and then test their ability in a range of environments, with some built specifically for testing of AI and others using things built for humans. Plus, not all information about the game board is available at once, meaning players have to make assumptions and predictions about what the opposition is up to.

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.

Altre relazioni OverNewsmagazine

Discuti questo articolo

SEGUI I NOSTRI GIORNALE