Category: CMUTR
Institution: Department of Computer Science, Carnegie
        Mellon University
Abstract: A fresh assessment of what autonomous agents are or may aspire 
        to be in presented in the paper.
        We dismiss the traditional dichotomy between reactive and 
        symbolic architectures.
        A Classification in terms of the amount of knowledge embedded in  		the system is made, instead, running from regulatory to planning
        to adaptive agents. 
        Regulatory agents are implementable as control systems or 
        automata, and represent the ideal case in which the agent has 
        all the knowledge it needs.
        We find that each type of agent is best suited for a particular
        kind of behavior.
        The different kinds of behavior from a hierarchy in terms of 
        frequency of occurrence and response time, and do not gracefully
        reduce to each other.
        This suggests implementing agents as hierarchies of simpler 
        agents, each specialized in the king of behavior it implements.
        In this scheme, agents at one level act through agents at the 
        next lower level.
        We introduce the concept of drive to address the issue of where 
        an agent's goals come from.
        A discussion is made of common pitfalls and suggestions for the 
        design of planning agents.
        Finally, a parallel architecture that embodies many of the ideas
        presented is sketched and discussed.
        This architecture solves the two major problems present in 
        Georgeff's earlier architecture, PRS: strictly sequential 
        execution, and inability to learn.
Number: CMU-CS-91-204
Bibtype: TechReport
Author: JOSE C.BRUSTOLONI Title:		
Year: 1991 Month:		
Address: Pittsburgh, PA
Super: @CMUTR