Re:DeepMind StarCraft II Demonstration [video]
by orbifold on Friday January 25, 2019 @02:33PM
(#19001591)
It makes the trained agent much less like a human, individual agents are not creative, they‘ve just learned to execute a certain build order. It might turn out that this is enough coupled with flawless execution and micro.
Re:DeepMind StarCraft II Demonstration [video]
by Dylan16807 on Friday January 25, 2019 @05:23PM
(#19003159)
"A human agent isn't creative, it just has a set of initial build orders it developed and picks one before the game starts, and after that it adapts to the situation weighted by the units it prefers."
Also the execution of the build order is nowhere near flawless.
The biggest effect is that it's harder to change strategy midgame, which is not all that critical.