An (isolated) world model is required for a number of AI applications. So we would like to separate world model* from agent** model, action model, any pre and post processors, etc. Specialist A.s.a. agents do this to some (limited) degree and even (partially) decompose the world model into specialized submodels*** (i.e., knowledge organization). The mechanisms at play in that case are the specialized (and limited) training curriculum plus the subsequent tasks and work environment selection.
* "laws of nature"?
** observer?
*** scientific fields?
No comments:
Post a Comment