RTS AI with an emphasis on StarCraft. It includes
particular research based on other RTS games in the
case that significant literature based on StarCraft is
not (yet) available in that area. The article begins by
outlining the different AI techniques used, grouped
by the area in which they are primarily applied.
These areas are tactical decision making, strategic
decision making, plan recognition, and learning.
This is followed by a comparison of the way game AI
is used in academe and the game industry, which
outlines the differences in goals and discusses the
low adoption of academic research in the industry.
Finally, some areas are identified in which there
does not seem to be sufficient research on topics
that are well-suited to study in the context of RTS
game AI. This last section also calls for standardiza-
tion of the evaluation methods used in StarCraft AI
Tactical Decision Making
Tactical and micromanagement decisions — control-
ling individual units or groups of units over a short
period of time — often make use of a different tech-
nique from the AI that makes strategic decisions.
These tactical decisions can follow a relatively simple
metric, such as attempting to maximize the amount
of enemy firepower that can be removed from the
playing field in the shortest time (Davis 1999). In the
video game industry, it is common for simple tech-
niques, such as finite state machines, to be used to
make these decisions (Buckland 2005). However,
even in these small-scale decisions, many factors can
Figure 2. Part of a Player’s Base in StarCraft.
The white rectangle on the minimap (bottom left) is the area visible on screen. The minimap shows areas that are unexplored (black),
explored but not visible (dark), and visible (light). It also shows the player’s forces (lighter dots) and last-seen enemy buildings (darker dots).
89 190 103/134
Terran Command Center
Supplies used: 103
Supplies provided: 10
Total supplies: 134
Supplies max: 200