Right on the MONEE combining task- and environment-driven evolution

E.W. Haasdijk, B.P.M. Weel, A.E. Eiben

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review


Evolution can be employed for two goals. Firstly, to provide a force for adaptation to the environment as it does in nature and in many artificial life implementations - this allows the evolving population to survive. Secondly, evolution can provide a force for optimisation as is mostly seen in evolutionary robotics research - this causes the robots to do something useful. We propose the monee algorithmic framework as an approach to combine these two facets of evolution: to combine environment-driven and task-driven evolution. To achieve this, monee employs environment-driven and task-based parent selection schemes in parallel. We test this approach in a simulated experimental setting where the robots are tasked to collect two different kinds of puck. Monee allows the robots to adapt their behaviour to successfully tackle these tasks while ensuring an equitable task distribution at no cost in task performance through a market-based mechanism. In environments that discourage robots performing multiple tasks and in environments where one task is easier than the other, monee's market mechanism prevents the population completely focussing on one task. Copyright © 2013 ACM.
Original languageEnglish
Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference
Place of PublicationAmsterdam
Number of pages8
Publication statusPublished - 2013
EventGenetic and Evolutionary Computation Conference (GECCO) -
Duration: 6 Jul 201310 Jul 2013


ConferenceGenetic and Evolutionary Computation Conference (GECCO)

Bibliographical note

haasdijk2013right-on-the-mo To Appear


  • Commerce
  • Multiobjective optimization
  • Embodied evolution
  • On-line evolution
  • Open-ended
  • Robots

Fingerprint Dive into the research topics of 'Right on the MONEE combining task- and environment-driven evolution'. Together they form a unique fingerprint.

Cite this