For example, while the objective of the game is to beat the opponent, the player must also carry out and balance a number of sub-goals, such as gathering resources or building structures.
DeepMind said that SC2LE's mini-games, which are created to test specific skills, have shown promising results in training and evaluating AI, but the company said that its strongest AI agents could not win a full Starcraft II match against even the easiest opponents. This also means that often players have to play the "long game", putting into place actions which may not play off until much later in the game. To succeed, a player needs to have a good memory, prioritize among tasks, and plan under conditions of uncertainty. 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 glut of players in both games competing online at high levels also gives researchers tons of replay data to use for training AI. "This kind of training will soon be far easier thanks to Blizzard, which has committed to on-going releases of hundreds of thousands of anonymized replays."DeepMind also said it was releasing a series of "mini-game" environments that will help researchers train their AI agents on basic components of the game".
"Our initial investigations show that our agents perform well on these mini games". DeepMind wants this to propel the existing research forward, hence its appeal to larger research community and this open release of tools.
DeepMind is an offshoot of Google that has scientific mission in mind, with the goal of developing Artificial Intelligence (AI) systems that have the ability to learn to solve complex problems.
"We've worked closely with the StarCraft II team to develop an API that supports something similar to previous bots written with a "scripted" interface, allowing programmatic control of individual units and access to the full game state (with some new options as well)", DeepMind said at the time.
An AI engine would therefore have to make use of the skills of memory, mapping, long-term planning, and adapting to changes in plans using information that is continually being gathered, which translates to hierarchical planning and reinforcement learning.