Evolution is often successful in generating complex behaviors, but evolving agents that exhibit distinctly different modes of behavior under different circumstances (multi-modal behavior) is both difficult and time consuming. This paper presents a method for encouraging the evolution of multi-modal behavior in agents controlled by artificial neural networks: A network mutation is introduced that adds enough output nodes to the network to create a new output mode. Each output mode completely defines the behavior of the network, but only one mode is chosen at any one time, based on the output values of preference nodes. With such structure, networks are able to produce appropriate outputs for several modes of behavior simultaneously, and arbitrate between them using preference nodes. This mutation makes it easier to discover interesting multi-modal behaviors in the course of neuroevolution.

[Winner of the Best Student Paper award at CIG'09]

PDF

In IEEE Symposium on Computational Intelligence and Games (CIG 2009), 325--332, Milan, Italy, September 2009. (Best Student Paper Award).

@inproceedings{schrum:cig09, title={Evolving Multi-modal Behavior in NPCs}, author={Jacob Schrum and Risto Miikkulainen}, booktitle={IEEE Symposium on Computational Intelligence and Games (CIG 2009)}, month={September}, address={Milan, Italy}, pages={325--332}, note={(Best Student Paper Award)}, url="http://nn.cs.utexas.edu/?schrum:cig09", year={2009} }

Slides (PPT)