Genetic Algorithms with a State Dependent Fitness Function

Herbert Dawid
Additional contact information
Herbert Dawid: University of Vienna, Department of Management Science

Chapter 4 in Adaptive Learning by Genetic Algorithms, 1999, pp 71-96 from Springer

Abstract: Abstract In the last chapter I have mainly reviewed existing literature and models, which have proven to be of great importance for the theoretical analysis of genetic algorithms. In this chapter we will deal with a new problem, which has not been dealt with in this literature1. The analytical models presented in chapter 3 all assume that the genetic algorithm is used to solve an optimization problem for an exogenously given fitness function. However, this is not the case if we think of an economic system, like a market, where the payoff of a single market member depends crucially on the actions of the rest of the market. The same argument holds also for two agents playing a normal form game, where the payoff of a strategy depends on the opponents’ strategy. In such models which are also often called co-evolutionary models two major aspects of the genetic algorithm change compared to its traditional application as an optimization tool. Firstly, the fitness of a single string depends on the state of the whole population. In an optimization problem the fitness values can be written in one r-dimensional vector f, but in economic systems the fitness is in general given by a r-dimensional function f:S→IRr, where f k (Ø) is the fitness of string k, when the whole population is in state Ø ∈S2. Secondly, we are no longer interested in the learning of optimal solutions, but rather in the question whether adaptive learning eventually leads to equilibrium behavior. As the simplest concept of an economic equilibrium we might say that the system is in equilibrium if the current action of every agent is optimal under the assumption, that all other agents behave according to the equilibrium. For later reference a formal definition of an economic equilibrium is given in definition 4.1.1. In what follows, I will often stress the term “economic” to distinguish it from dynamic equilibria.

Keywords: Genetic Algorithm; Crossover Operator; Mutation Probability; Binary String; Markov Chain Model (search for similar items in EconPapers)
Date: 1999
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-18142-9_4

Ordering information: This item can be ordered from
http://www.springer.com/9783642181429

DOI: 10.1007/978-3-642-18142-9_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().