The Influence of Fitness Function on Quality of Neuro-Controllers Produced with Assembler Encoding

Tomasz Praczyk

doi:10.4028/www.scientific.net/SSP.180.89

Paper Titles

The Multistage Positional Game of Marine Objects with Different Degree of Cooperation
p.56

The Optimal and Safe Ship Trajectories for Different Forms of Neural State Constraints
p.64

Safe Ship’s Control in a Fuzzy Environment Using a Genetic Algorithm
p.70

Possibility of Automation of a Mobile Biodiesel Production Plant
p.76

The Influence of Fitness Function on Quality of Neuro-Controllers Produced with Assembler Encoding
p.89

Analysis of Interactions between Pilot-Operator and Advanced Flight Control System
p.101

Decision-Making Processes in Transport Telematic Systems Exploitations
p.109

Comparison of Centralized, Dispersed and Hybrid Multiagent Control Systems of Underwater Vehicles Team
p.114

Power Distribution in Propulsion System of Semiautonomous Underwater Vehicle
p.125

HomeSolid State PhenomenaSolid State Phenomena Vol. 180The Influence of Fitness Function on Quality of...

The Influence of Fitness Function on Quality of Neuro-Controllers Produced with Assembler Encoding

Abstract:

Assembler Encoding is a neuro-evolutionary method in which neural networks are represented in the form of evolutionary created programs. Each program consists of operations and data evolving in many separate populations. To enable the evolution to produce effective programs and in consequence neural networks, operations and data from each population have to be reliably evaluated. The paper presents and compares several methods that can be used for that purpose. The comparative tests were carried out on the predator-prey problem.