10.4225/03/570EE6833FC2E
Nader Chmait
Nader
Chmait
David L Dowe
David L
Dowe
David G Green
David G
Green
Yuan-Fang Li
Yuan-Fang
Li
Javier Insa-Cabrera
Javier
Insa-Cabrera
Measuring Universal Intelligence in Agent-Based Systems Using the Anytime Intelligence Test
Monash University
2016
universal intelligence
anytime intelligence test
agent
Adaptive Agents and Intelligent Robotics
Artificial Intelligence and Image Processing
2016-04-14 00:38:25
Report
https://bridges.monash.edu/articles/report/Measuring_Universal_Intelligence_in_Agent_Based_Systems_Using_the_Anytime_Intelligence_Test/3175585
Abstract. This paper aims to quantify and analyze the intelligence of artificial agent collectives. A universal metric is proposed and used to empirically measure intelligence for several different agent decision controllers. Accordingly, the effectiveness of various algorithms is evaluated on a per-agent basis over a selection of abstracted, canonical tasks of different algorithmic complexities. Results reflect the different settings over which cooperative multiagent systems can be significantly more intelligent per agent than others. We identify and discuss some of the factors in influencing the collective performance of these systems <br>