Imitation learning at all levels of game-AI
Christian Thurau, Christian Bauckhage, Gerhard Sagerer · 2004
Imitation is a powerful mechanism the human brain applies to extend its repertoire of solutions and behaviors suitable to solve problems of various kinds. From an abstract point of view, the major advantage of this strategy is that it re-duces the search space of apropriate solutions. In this con-tribution, we discuss if and how the principle of imitation learning can facilitate the programing of life-like computer game charecters. We present different algorithms that learn from human generated training data and we show that ma-chine learning can be applied on different levels of cognitive abstraction.