Skip navigation
PDF 702 KB
Page 174
First published 20 July 2015

Evolving Collective Behaviors With Diverse But Predictable Sensor States

Payam Zahadat, Heiko Hamann, and Thomas Schmickl

Abstract (Excerpt)

Artificial evolution of collective behaviors can be implemented in different ways. Here, we extend the approach of Hamann (2014). The underlying concept is that the brain is permanently trying to predict future perceptions and a state of well-being is a state that allows for precise predictions (Friston, 2010). Striving for maximal prediction success needs to be complemented by a force that implements curiosity and exploration. In this abstract we present an extended method diverse-prediction that rewards not only for correct predictions but also for each visited sensory state. This proves to be a better approach compared to the method prediction (Hamann, 2014).