State and Action Abstraction in the Development of Agent Controllers
Ellie Brent, F. Dean · InTech eBooks · 2010
The most significant result of these experiments is that, in the problem domains used in this chapter, the abstraction of an agent's action space provided more tangible benefits in the development of agent controllers than abstraction of an agent's state space. In a direct comparison, controllers that used significant action abstraction and no state abstraction had higher performance and were developed faster than controllers that made extensive use of state abstraction and moderate action abstraction. This is due to the fact that action abstraction changed the focus of the controller from one of low-level control to one of high-level coordination. This change in focus not only made the development of controllers for complex composite tasks more practical, but in many of the tasks, it also allowed the controller to have higher performance. One aspect that is fundamental to the improved performance and rate of development of controllers using adaptive fuzzy behavior hierarchies was the ability to reuse existing primitive and composite behaviors. The ability to reuse, without modification, behaviors developed for one task in another task allowed for the development of controllers in individual pieces. The benefits of this approach are apparent when compared to the other approaches evaluated in these experiments which attempted to develop a controller all at once. As a result of this