DeepMind has teamed up with Blizzard to turn StarCraft II into an AI research environment: being that the classic RTS is highly varied and complex, it’s an ideal platform for advancing the potential of AI and gauging just how well it can measure up to real gamers and the human mind. The collaboration has already resulted in a Blizzard-developed API that gives researchers and developers hooks into the game, as well as a massive dataset of anonymized game replays.



The game also has other qualities that appeal to researchers, such as the large pool of avid players that compete online every day. This ensures that there is a large quantity of replay data to learn from – as well as a large quantity of extremely talented opponents for AI agents. Even StarCraft’s action space presents a challenge with a choice of more than 300 basic actions that can be taken. Contrast this with Atari games, which only have about 10 (e.g. up, down, left, right etc). On top of this, actions in StarCraft are hierarchical, can be modified and augmented, with many of them requiring a point on the screen. Even assuming a small screen size of 84×84 there are roughly 100 million possible actions available.

Discussion

Source: [H]ardOCP – StarCraft May Be the Next Game That AI Beats Us At