Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Intelligent Mutation Rate Control in Canonical Genetic Algorithms
ISMIS '96 Proceedings of the 9th International Symposium on Foundations of Intelligent Systems
| Hi-index | 0.00 |
This paper explores the question whether boundedly rational agents learn to behave optimally when asked to voluntarily contribute to a public good. The dynamic game is described by an Evolutionary Algorithm, which is shown to extend the applicability of ordinary replicator dynamics of evolutionary game theory to problem sets characterized by finite populations and continuous strategy spaces. We analyze the learning process of purely and impurely altruistic agents and find in both cases the contribution level to converge towards the Nash equilibrium. The group size, the degree of initial heterogeneity and the propensity to experiment are key factors of the learning process.