The agent network architecture (ANA)

ABSTRACT

The goal of my work is to develop and implement an architecture for an autonomous agent, which I refer to as "ANA". An ANA agent consists of a distributed set of "competence modules". Competence modules are linked in a network. A spreading activation process operates on the network to decide what the "relevance" or relative strength of a competence module is in the current context. This process implements a competition among modules for activation energy. The higher the activation energy level of a module, the more likely it is that this module determines what the autonomous agent does or communicates to believe. Learning is a central, completely integrated feature of the architecture. The competence module network is continuously being developed and changed on the basis of experience: links are added and deleted depending on real world observations and new "macro modules" are created whenever a goal is achieved. This paper presents an overview of the architecture. It describes the functionalities that have been implemented, the results that have been obtained with robotic and simulated ANA agents, and finally it discusses (current) limitations and future work.

REFERENCES

• 1: Agre, P. & Chapman, D. Pengi: An Implementation of a Theory of Activity, Proceedings of AAAI-87, Morgan Kaufmann, Los Altos, California, 1987.
• 2: Brooks, R. A Robust Layered Control System for a Mobile Robot. IEEE Journal of Robotics and Automation. Volume RA-2, Number 1, 1986.
• 3: John E. Laird , Paul S. Rosenbloom , Allen Newell, Chunking in Soar: The Anatomy of a General Learning Mechanism, Machine Learning, v.1 n.1, p.11-46 [doi>10.1023/A:1022639103969]
• 4: Maes, P. The Dynamics of Action Selection. Proceedings of the IJCAI-89 conference, Detroit, 1989.
• 5: Maes, P. How To Do the Right Thing. Connection Science Journal. 1(3). 1989b.
• 6: Maes, P. and Brooks, R.A. Learning to Coordinate Behaviors. Proceedings of AAAI-90, 1990.
• 7: Maes, P. Situated Agents can Have Goals. In: Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back. P. Maes (editor). Special Issue of the Journal Robotics and Autonomous Systems. 6(1&2). Also MIT-Bradford Press book, 1991.
• 8: Pattie Maes, A bottom-up mechanism for behavior selection in an artificial creature, Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats, p.238-246, February 1991, Paris, France
• 9: Maes, P. Adaptive Action Selection. Submitted to the Cognitive Science Conference 1991, 1991c.
• 10: Maes, P. How to Learn to Do the Right Thing Submitted to the European ALIFE Conference 1991, 1991d.
• 11: Marvin Minsky, The society of mind, Simon & Schuster, Inc., New York, NY, 1986

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Performance, Theory