An Investigation of How Humans and Machines Deal with Increases in Reactivity

Abstract : Many aspects of CGF tasks have highly reactive aspects to them "e.g., observing and responding to multiple simultaneous information sources while piloting an airplane". Also, reactivity can be a critical aspect of performance when there are many individual agents being controlled. This reactivity, however, must be combined with "higher-level" cognitive activities like planning and strategy assessment. Finally, reactivity and planning activities must coexist in a single system that interacts realistically with the environment. This preliminary work presents an initial examination of reactivity in SAMUEL agents and humans.

[1]  Alan C. Schultz,et al.  Using a Genetic Algorithm to Learn Strategies for Collision Avoidance and Local Navigation. , 1990 .

[2]  Annie S. Wu,et al.  Evolving control for distributed micro air vehicles , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[3]  John J. Grefenstette,et al.  Evolutionary Algorithms for Reinforcement Learning , 1999, J. Artif. Intell. Res..

[4]  C. Lebiere,et al.  The Atomic Components of Thought , 1998 .

[5]  K. A. Ericsson,et al.  Protocol Analysis: Verbal Reports as Data , 1984 .

[6]  John E. Laird,et al.  An Exploration into Computer Games and Computer Generated Forces , 2000 .