Download:
|
by Byoung-tak Zhang, Dong-yeon Cho
http://bi.snu.ac.kr/Publications/Books/aigp3.ps
Add To MetaCart
Abstract:
Genetic programming provides a useful paradigm for developing multiagent systems in the domains where human programming alone is not sufficient to take into account all the details of possible situations. However, existing GP methods attempt to evolve collective behavior immediately from primitive actions. More realistic tasks require several emergent behaviors and a proper coordination of these is essential for success. We have recently proposed a framework, called fitness switching, to facilitate learning to coordinate composite emergent behaviors using genetic programming. Coevolutionary fitness switching described in this chapter extends our previous work by introducing the concept of coevolution for more effective implementation of fitness switching. Performance of the presented method is evaluated on the table transport problem and a simple version of simulated robot soccer problem. Simulation results show that coevolutionary fitness switching provides an effective mechanism for learning complex collective behaviors which may not be evolved by simple genetic programming.
Citations
|
193
|
Francone, Genetic Programming: An Introduction on the Automatic Evolution of Computer Programs and Its Applications. organ
– Banzhaf, Nordin, et al.
- 1989
|
|
169
|
Genetic programming: on the programming of computers by natural selection
– Koza
- 1992
|
|
116
|
RoboCup: A challenging problem for AI
– Kitano, Asada, et al.
- 1997
|
|
65
|
Collective Robotics: From Social Insects to Robots. Adaptive Behavior
– Kube, Zhang
- 1993
|
|
57
|
Co-evolving soccer softbot team coordination with genetic programming
– Luke, Hohn, et al.
- 1997
|
|
49
|
Evolving teamwork and coordination with genetic programming
– Luke, Spector
- 1996
|
|
42
|
Emergent hierarchical control structures: Learning reactive/hierarchical relationships in reinforcement environments
– Digney
- 1996
|
|
37
|
Coordination and Learning in Multi-Robot Systems
– Mataric
- 1998
|
|
28
|
Evolving a Team
– Haynes, Sen, et al.
- 1995
|
|
26
|
Evolution of herding behavior in artificial animals
– Werner, Dyer
- 1993
|
|
17
|
Data Structures and Genetic
– Langdon
- 1998
|
|
15
|
Automatic creation of an efficient multi-agent architecture using genetic programming with architecture-altering operations
– Bennett
- 1996
|
|
6
|
The Application of Genetic Programming to the Automatic Generation of Object-Oriented Programs
– Bruce
- 1995
|
|
6
|
Multiple-agent learning for a robot navigation task by genetic programming
– Iba
- 1997
|
|
4
|
Fitness switching: Evolving complex group behaviors using genetic programming
– Zhang, Cho
- 1998
|
|
1
|
Learning soccer-robot cooperation strategies using genetic programming
– Cho, Zhang
- 1998
|
|
1
|
volume 1042 of LNCS, pp 152--163
– Sen
|
|
1
|
Evolving agents," in Genetic Programming 1996
– Qureshi
- 1996
|
|
1
|
A multiple neural architecture for evolving collective robotic intelligence
– Zhang, Hong
- 1997
|
