Evolving Multimodal Networks for Multitask Games

Title

Evolving Multimodal Networks for Multitask Games

Description

This is an Accepted Manuscript of an article published by IEEE. Schrum, J., & Miikkulainen, R. (2012). Evolving Multimodal Networks for Multitask Games. IEEE Transactions on Computational Intelligence and AI in Games, 4(2), 94–111. https://doi.org/10.1109/TCIAIG.2012.2193399. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.")

Creator

Schrum, Jacob

Miikkulainen, Risto

Date

2016-12-13

Date Available

2016-12-13

Date Issued

2012

Identifier

Schrum, J., & Miikkulainen, R. (2012). Evolving Multimodal Networks for Multitask Games. IEEE Transactions on Computational Intelligence and AI in Games, 4(2), 94–111. https://doi.org/10.1109/TCIAIG.2012.2193399

uri

https://collections.southwestern.edu/s/suscholar/item/229

Abstract

Intelligent opponent behavior makes video games interesting to human players. Evolutionary computation can discover such behavior, however, it is challenging to evolve behavior that consists of multiple separate tasks. This paper evaluates three ways of meeting this challenge via neuroevolution: 1) multinetwork learns separate controllers for each task, which are then combined manually; 2) multitask evolves separate output units for each task, but shares information within the network's hidden layer; and 3) mode mutation evolves new output modes, and includes a way to arbitrate between them. Whereas the fist two methods require that the task division be known, mode mutation does not. Results in Front/Back Ramming and Predator/Prey games show that each of these methods has different strengths. Multinetwork is good in both domains, taking advantage of the clear division between tasks. Multitask performs well in Front/Back Ramming, in which the relative difficulty of the tasks is even, but poorly in Predator/Prey, in which it is lopsided. Interestingly, mode mutation adapts to this asymmetry and performs well in Predator/Prey. This result demonstrates how a human-specified task division is not always the best. Altogether the results suggest how human knowledge and learning can be combined most effectively to evolve multimodal behavior.

Language

English

Publisher

IEEE

Subject

Computer games

Evolutionary computation

Approximation methods

Multimodal networks

Multitask games

Multitask Learning

Mode Mutation

Type

Article