Evolving Multimodal Networks for Multitask Games
Authors:
- 6 April 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Intelligence and AI in Games
- Vol. 4 (2) , 94-111
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.Keywords
This publication has 29 references indexed in Scilit:
- Evolving agent behavior in multiobjective domains using fitness-based shaping2010
- Genetic Team Composition and Level of Selection in the Evolution of CooperationIEEE Transactions on Evolutionary Computation, 2009
- Evolving neural networks for strategic decision-making problemsNeural Networks, 2009
- The Hypervolume Indicator Revisited: On the Design of Pareto-compliant Indicators Via Weighted Integration2007
- Evolving Stochastic Controller Networks for Intelligent Game Agents2006
- Automatic feature selection in neuroevolution2005
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- An Overview of Evolutionary Algorithms in Multiobjective OptimizationEvolutionary Computation, 1995
- A robust layered control system for a mobile robotIEEE Journal on Robotics and Automation, 1986