Evolving agent behavior in multiobjective domains using fitness-based shaping

Title

Evolving agent behavior in multiobjective domains using fitness-based shaping

Description

This is an Accepted Manuscript of an article published by ACM. Schrum, J., & Miikkulainen, R. (2010). Evolving Agent Behavior in Multiobjective Domains Using Fitness-based Shaping. In Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation (pp. 439–446). New York, NY, USA: ACM. https://doi.org/10.1145/1830483.1830567

Creator

Schrum, Jacob

Miikkulainen, Risto

Date

2016-12-13

Date Available

2016-12-13

Date Issued

2010

Identifier

Schrum, J., & Miikkulainen, R. (2010). Evolving Agent Behavior in Multiobjective Domains Using Fitness-based Shaping. In Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation (pp. 439–446). New York, NY, USA: ACM. https://doi.org/10.1145/1830483.1830567

uri

https://collections.southwestern.edu/s/suscholar/item/232

Abstract

Multiobjective evolutionary algorithms have long been applied to engineering problems. Lately they have also been used to evolve behaviors for intelligent agents. In such applications, it is often necessary to "shape" the behavior via increasingly difficult tasks. Such shaping requires extensive domain knowledge. An alternative is fitness-based shaping through changing selection pressures, which requires little to no domain knowledge. Two such methods are evaluated in this paper. The first approach, Targeting Unachieved Goals, dynamically chooses when an objective should be used for selection based on how well the population is performing in that objective. The second method, Behavioral Diversity, adds a behavioral diversity objective to the objective set. These approaches are implemented in the popular multiobjective evolutionary algorithm NSGA-II and evaluated in a multiobjective battle domain. Both methods outperform plain NSGA-II in evolution time and final performance, but differ in the profiles of final solution populations. Therefore, both methods should allow multiobjective evolution to be more extensively applied to various agent control problems in the future.

Language

English

Publisher

ACM

Subject

Multiobjective evolution

Algorithms

Evolving agent behavior

Fitness-based shaping

Type

Article