Evolving Cooperative Actions Among Heterogeneous Agents by an Evolutionary Programming Method

Authors:
Takayuki Fujinaga;Kousuke Moriwaki;Nobuhiro Inuzuka;Hidenori Itoh
Affiliations:
-;-;-;-
Venue:
SEAL'98 Selected papers from the Second Asia-Pacific Conference on Simulated Evolution and Learning on Simulated Evolution and Learning
Year:
1998

Citing 2
Cited 0

An adaptive communication protocol for cooperating mobile robots

Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Leaning to behave socially

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3

Quantified Score

Hi-index	0.01

Visualization

Abstract

We studied a baggage carriage problem, in which agents try to carry baggage from a pile to their base, evolving a data structure, called n-BDD, expressing action strategy of the agents. Through this problem we consider emergence of cooperation among heterogeneous agents, or each agent has a particular ability, which is different each other. We formalize heterogeneity by defining forte actions and foible actions of agents. Emergence of cooperation was observed by simulation. Different types of agents are emerged to behave different way. We also observed that agents in a type branch to have two different roles.