Understanding behaviors of a constructive memory agent: A markov chain analysis

Authors:
John S. Gero;Wei Peng
Affiliations:
Krasnow Institute for Advanced Study, Mailstop 2A1, George Mason University, Fairfax, VA 22030, USA and UTS, Australia;School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V, Melbourne, VIC 3001, Australia
Venue:
Knowledge-Based Systems
Year:
2009

Citing 10
Cited 2

SOAR: an architecture for general intelligence

Artificial Intelligence
A Compression Algorithm for Probability Transition Matrices

SIAM Journal on Matrix Analysis and Applications
Situated Cognition: On Human Knowledge and Computer Representations

Situated Cognition: On Human Knowledge and Computer Representations
Constructing Intelligent Agents with Java: A Programmer's Guide to Smarter Applications

Constructing Intelligent Agents with Java: A Programmer's Guide to Smarter Applications
Design by Optimization in Architecture, Building, and Construction

Design by Optimization in Architecture, Building, and Construction
Constructive memory for situated design agents

Artificial Intelligence for Engineering Design, Analysis and Manufacturing
Extending the Soar Cognitive Architecture

Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Extending cognitive architecture with episodic memory

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Using a constructive interactive activation and competition neural network to construct a situated agent's experience

PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Understanding situated design computing and constructive memory: newton, mach, einstein and quantum mechanics

EG-ICE'06 Proceedings of the 13th international conference on Intelligent Computing in Engineering and Architecture

Situated Computation

Proceedings of the 2009 conference on New Trends in Software Methodologies, Tools and Techniques: Proceedings of the Eighth SoMeT_09
Trajectory analysis for user verification and recognition

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a Markov chain analysis of the behaviors of a constructive memory agent. It shows that a constructive memory agent behaves based on the knowledge structures that it has learned from its interaction with the environment. The internal reasoning moves from reactive and reflective to reflexive as the agent acquires more experiences that are increasingly grounded.