Neuro-evolution for a gathering and collective construction task

In this paper we apply three Neuro-Evolution (NE) methods as controller design approaches in a collective behavior task. These NE methods are Enforced Sub-Populations, MultiAgent Enforced Sub-Populations, and Collective Neuro- Evolution. In the collective behavior task, teams of simulated robots search an unexplored area for objects that are to be used in a collective construction task. Results indicate that the Collective Neuro-Evolution method, a cooperative co-evolutionary approach that allows for regulated recombination between genotype populations is appropriate for deriving artificial neural network controllers in a set of increasingly difficult collective behavior task scenarios. Categories and Subject Descriptors I.2.11 [Distributed Artificial Intelligence]: Intelligent agents General Terms Algorithms Keywords Neuro-Evolution, Collective Behavior, Specialization

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: D. W. F. van Krevelen, Geoff S. Nitschke
• Keywords: Collective Behavior Task, Collective Construction Task, Collective Neuro-Evolution, GECCO 2008, Optimization