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 de-sired 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, re-member, 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 de-sired 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. © 2014 ACM.
Lehman, J., & Miikkulainen, R. (2014). Overcoming deception in evolution of cognitive behaviors. In GECCO 2014 - Proceedings of the 2014 Genetic and Evolutionary Computation Conference (pp. 185–192). Association for Computing Machinery. https://doi.org/10.1145/2576768.2598300