AlphaStar explained: Grandmaster level in StarCraft II with multi-agent RL

Описание: For slides and more information on the paper, visit https://aisc.ai.science/events/2019-1...

Discussion lead: Gordon Gibson
Discussion facilitator(s): Alok Deshpande, Xiyang Chen

Correction: in the video it was stated that 128 TPU's are used for training. The actual number was 32.

From the official website:

TL;DR: AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. This January, a preliminary version of AlphaStar challenged two of the world's top players in StarCraft II, one of the most enduring and popular real-time strategy video games of all time. Since then, we have taken on a much greater challenge: playing the full game at a Grandmaster level under professionally approved conditions.

Our new research differs from prior work in several key regards:
1. AlphaStar now has the same kind of constraints that humans play under – including viewing the world through a camera, and stronger limits on the frequency of its actions* (in collaboration with StarCraft professional Dario “TLO” Wünsch).
2. AlphaStar can now play in one-on-one matches as and against Protoss, Terran, and Zerg – the three races present in StarCraft II. Each of the Protoss, Terran, and Zerg agents is a single neural network.
3. The League training is fully automated, and starts only with agents trained by supervised learning, rather than from previously trained agents from past experiments.
4. AlphaStar played on the official game server, Battle.net, using the same maps and conditions as human players. All game replays are available here.