Filter

  • Advanced Filters:

  • to
  • Specific Data Sources:

    All Edit

    Select All  |  Select None

Reset filters

DeepDyve - Search, Rent, Read
The easiest way for you to get scholarly articles:

  • Millions of articles from over 6,000 authoritative journals.
  • Get any 40 rentable articles for just $40 a month.
  • Read rented articles for an entire year.
  • Unused rentals get rolled over.

Bookmark

The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction

Doya,Kenji; Uchibe,Eiji
Adaptive Behavior , Volume 13 (2): 149 SAGEJun 1, 2005

Preview Only

The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction

Abstract

The aim of the Cyber Rodent project is to understand the origins of our reward and affective systems by building artificial agents that share the same intrinsic constraints as natural agents: Self-preserva tion and self-reproduction. A Cyber Rodent is a robot that can search for and recharge from battery packs on the floor and copy its programs to a nearby agent through its infrared communication port. This article reviews our research topics so far, including (1) evolution of neural controllers, (2) learning of foraging and mating behaviors, (3) evolution of learning architectures and meta-parameters, (4) simultaneous learning of multiple agents in a body, and (5) learning and evolution in a self-sustained colony. We discuss our future directions and expected contributions.
Loading next page...
1 Page

Preview Only. This article cannot be rented because we do not currently have permission from the publisher.

 
/lp/sage/the-cyber-rodent-project-exploration-of-adaptive-mechanisms-for-self-Hxcic7bbig
Title
The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction
Author(s)
Doya,Kenji; Uchibe,Eiji
Journal
Adaptive Behavior , Volume 13 (2): 149 SAGE – Jun 1, 2005
Publisher
Sage Publications
Copyright
Copyright © 2005 by SAGE Publications
ISSN
1059-7123
eISSN
1059-7123
D.O.I.
10.1177/105971230501300206
Publisher site
Get PDF