@inproceedings{lehman:gecco14,
    author = "Lehman, Joel and Miikkulainen, Risto",
    title = "Overcoming Deception in Evolution of Cognitive Behaviors",
    booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014)",
    month = "July",
    address = "Vancouver, BC, Canada",
    url = "http://nn.cs.utexas.edu/?lehman:gecco14",
    year = "2014",
    site = "http://nn.cs.utexas.edu/?lehman:gecco14",
    abstract = "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."
}