Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments

  • Edward Robinson
  • Timothy Ellis
  • Alastair Channon
Conference paper

DOI: 10.1007/978-3-540-74913-4_35

Volume 4648 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Robinson E., Ellis T., Channon A. (2007) Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments. In: Almeida e Costa F., Rocha L.M., Costa E., Harvey I., Coutinho A. (eds) Advances in Artificial Life. ECAL 2007. Lecture Notes in Computer Science, vol 4648. Springer, Berlin, Heidelberg

Abstract

Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network architectures inside an animat: one that controls their high level deliberative behaviours, such as the selection of sub-goals, and one that provides reactive and navigational capabilities. Animats using this model are evolved in novel and dynamic environments, on complex tasks requiring deliberative behaviours: tasks that cannot be solved by reactive mechanisms alone and which would traditionally have their solutions formulated in terms of search-based planning. Significantly, no a priori information is given to the animats, making explicit forward search through state transitions impossible. The complexity of the problem means that animats must first learn to solve sub-goals without receiving any reward. Animats are shown increasingly complex versions of the task, with the results demonstrating, for the first time, incremental neuro-evolutionary learning on such tasks.

Keywords

Artificial Life Neural Networks Incremental Evolution Reactive and Deliberative Systems Novel and Dynamic Environments 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Edward Robinson
    • 1
  • Timothy Ellis
    • 1
  • Alastair Channon
    • 1
  1. 1.School of Computer Science, University of Birmingham, Birmingham, B15 2TTUK