Google and Blizzard launch a new AI research platform for RTS games

AI research

AI managed to defeat the best Dota 2 players in the world in 1-vs-1 matches at Valve’s recent tournament. It appears that artificial intelligence is going to play an important role in real-time strategy games in the future, as two tech giants shook hands and launched a new AI research platform for RTS games.

Google’s DeepMind AI research company and Blizzard recently released the StarCraft II API. Researchers, gamers, and hobbyists can now use this platform as a tool to contribute to AI research advancement. Blizzard explains that  this API also features a sandbox for the community to experiment with, using both learning based AI and scripted AI to build new tools for the game.

The StarCraft II AI research platform

The SC2LE includes the following tools:

  • A Machine Learning API developed by Blizzard that gives researchers and developers hooks into the game. This includes the release of tools for Linux for the first time.

  • A dataset of anonymised game replays, which will increase from 65k to more than half a million in the coming weeks.

  • An open source version of DeepMind’s toolset, PySC2, to allow researchers to easily use Blizzard’s feature-layer API with their agents.

  • A series of simple RL mini-games to allow researchers to test the performance of agents on specific tasks.

  • A joint paper that outlines the environment, and reports initial baseline results on the mini-games, supervised learning from replays, and the full 1v1 ladder game against the built-in AI.

StarCraft II and AI

StarCraft 2 is a complex multi-layered game and this makes it an ideal environment for AI research. The main objective of the game is to defeat your opponent. There are also many sub-goals that players must balance. To make things even more difficult, actions do not pay for a long-time and the map is only partially visible. This means that AI agents must imagine and plan ahead. Of course, this won’t be too difficult a task for Google’s AI agents, as the company already built AI bot that can imagine and predict the consequences of their actions.

StarCraft II also has a large pool of avid players that can provide AI bots with a large quantity of replay data to learn from.

Who knows, maybe next year we’ll hear about Google’s AI agents defeating the best StarCraft II players in the world.

Follow The AI Center on social media:

Maddie Blau

I strongly believe that Artificial Intelligence is the future of technology. AI research has yielded significant advancements in recent years and this is only the beginning.

Join me as I track the latest progress in AI research.
AI stock exchange
AI in real life
Canada’s first AI exchange-traded fund enters the market

  Canada launched the first artificial intelligence exchange-traded fund with the ticker MIND. The Horizons Active A.I. Global Equity ETF is an investment strategy run by an AI system. The AI algorithm analyzes financial data to extract patterns in order to determine what are the best investments to make. MIND …

smartest AI
AI research
Are you curious to see who’s the smartest AI in the world?

  The AI world is dominated by fierce competition. Well-known tech giants such as Google, Microsoft, Intel, NVIDIA and other are working at full speed to push AI research forward and innovate the field. The question is: who’s the smartest AI in the world? This is a very difficult question …

google assistant natural sound voice
AI research
Google Assistant’s voice is now more realistic thanks to WaveNet

Getting speech synthesis algorithms to sound natural is a hard nut to crack. AI researchers have been struggling to make digital assistants sound more natural for years, and the results are indeed impressive. However, there’s still something that doesn’t sound right and users can always tell if they’re talking to …