Overcoming Deception in Evolution of Cognitive Behaviors

Joel Lehman, Risto Miikkulainen

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationGenetic and Evolutionary Computation Conference : GECCO '14 Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation
PublisherAssociation for Computing Machinery
Publication date2014
Pages185-192
ISBN (Print)9781450326629
DOIs
Publication statusPublished - 2014

Keywords

  • $$evolution
  • $$modeling
  • cognition
  • diversity maintenance
  • evolutionary robotics

Cite this