Overcoming Deception in Evolution of Cognitive Behaviors (2014)
When scaling neuroevolution to complex behaviors, cognitive capabilities such as learning, communication, and memory become increasingly important. However, successfully evolving such cognitive abilities remains difficult. This paper argues that a main cause for such difficulty is deception, i.e. evolution converges to a behavior unrelated to the desired solution. More specifically, cognitive behaviors often require accumulating neural structure that provides no immediate fitness benefit, and evolution often thus converges to non-cognitive solutions. To investigate this hypothesis, a common evolutionary robotics T-Maze domain is adapted in three separate ways to require agents to communicate, remember, and learn. Indicative of deception, evolution driven by objective-based fitness often converges upon simple non-cognitive behaviors. In contrast, evolution driven to explore novel behaviors, i.e. novelty search, often evolves the desired cognitive behaviors. The conclusion is that open-ended methods of evolution may better recognize and reward the stepping stones that are necessary for cognitive behavior to emerge.
View:
PDF
Citation:
To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014), Vancouver, BC, Canada, July 2014.
Bibtex:

Joel Lehman Postdoctoral Alumni joel [at] cs utexas edu
Risto Miikkulainen Faculty risto [at] cs utexas edu