FEFFuL: A Few-Examples Fitness Function Learner
CEUR WORKSHOP PROCEEDINGS, 2021•iris.uniroma1.it
This paper presents FEFFuL, an architecture used to estimate the fitness value of a
generated artifact in any Evolution Strategy (ES) system that would otherwise require human
evaluation, ie: Interactive Evolutionary Computation (IEC) systems. By learning directly
human preferences, the FEFFuL network aims to reduce user's fatigue to a minimum while
also adapting to new emergent artifacts. We apply here FEFFuL in the context of evaluating
generated structures in the popular game Minecraft.
generated artifact in any Evolution Strategy (ES) system that would otherwise require human
evaluation, ie: Interactive Evolutionary Computation (IEC) systems. By learning directly
human preferences, the FEFFuL network aims to reduce user's fatigue to a minimum while
also adapting to new emergent artifacts. We apply here FEFFuL in the context of evaluating
generated structures in the popular game Minecraft.
Abstract
This paper presents FEFFuL, an architecture used to estimate the fitness value of a generated artifact in any Evolution Strategy (ES) system that would otherwise require human evaluation, ie: Interactive Evolutionary Computation (IEC) systems. By learning directly human preferences, the FEFFuL network aims to reduce user's fatigue to a minimum while also adapting to new emergent artifacts. We apply here FEFFuL in the context of evaluating generated structures in the popular game Minecraft.
iris.uniroma1.it
Showing the best result for this search. See all results