Overview of the agents' macro-micro hierarchical actions
But in just a couple of days training, the TSTARBOTS were able to defeat the traditional AI opponent on the hardest setting. The training used the Abyssal Reef, a map known to have thwarted neural network AIs from winning against SC2's built-in AIs.
The agents were trained by playing a 1 on 1 game, both using the Zerg race.
The macro-micro controller consists of several modules capable of handling entire facets of the gameplay independently. The second agent, the TSTARBOT2, is a more robust agent. The first agent acts as a macro-level controller that oversees several specific algorithms designed to handle lower level functions. In a published white paper, the researchers explained the creation of the two agents, named TSTARBOT1 and TSTARBOT2.
This makes the company the first to do so. This time, researchers from Chinese technology giant Tencent have developed a pair of AI agents capable of defeating StarCraft II’s (SC2) AI on the highest difficulty levels in full matches. Curious as we can be, we just love to test AIs by making them play games.
