I'm really interested in A.I, but I'm confused; I read this article:
It breaks down a complex A.I algorithm to an simple FSM, but isn't a A.I supposed to learn, in this article the transitions from state to state are simple conditions, i see nothing where this I.A is supposed to learn, this transitions are hardcoded, why the author calls it A.I ?
The same with behaviour tree, it's basically the same concept but different, self-contained collection of states for example this article:
http://blog.renatopp.com/2014/09/24/implementing-a-behavior-tree-part-1/
I think the only one's that learn are neural networks, or not?
Between is a neural network a A.I and a A.I a neural network, or is it not the same?
I think A.I is a "Category" and a neural network a more specific A.I.
It's a matter of semantics. What people usually call "Game AI" is not the same as AI as the field of computer science.
From the Wikipedia:
"In video games, artificial intelligence is used to generate intelligent behaviors primarily in non-player characters (...) However, the term game AI is often used to refer to a broad set of algorithms that also include techniques from control theory, robotics, computer graphics and computer science in general. (...) Since game AI for NPCs is centered on appearance of intelligence and good gameplay within environment restrictions, its approach is very different from that of traditional AI; workarounds and cheats are acceptable and, in many cases, the computer abilities must be toned down to give human players a sense of fairness. This, for example, is true in first-person shooter games, where NPCs' otherwise perfect aiming would be beyond human skill."
So, most game AI is not really intelligent and don't need to learn.
And by the way, Neural networks are not the only ones that learn.