Evolving coordinated spatial tactics for autonomous entities using influence maps

Authors:
Phillipa Avery;Sushil Louis;Benjamin Avery
Affiliations:
Evolutionary Computing Systems Laboratory, Dept. of Computer Science and Engineering, University of Nevada, Reno, Nevada;Evolutionary Computing Systems Laboratory, Dept. of Computer Science and Engineering, University of Nevada, Reno, Nevada;
Venue:
CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Year:
2009

Citing 5
Cited 2

Co-evolving real-time strategy game players

Co-evolving real-time strategy game players
Using coevolution to understand and validate game balance in continuous games

Proceedings of the 10th annual conference on Genetic and evolutionary computation
A model of visual organization for the game of GO

AFIPS '69 (Spring) Proceedings of the May 14-16, 1969, spring joint computer conference
Combining influence maps and cellular automata for reactive game agents

IDEAL'05 Proceedings of the 6th international conference on Intelligent Data Engineering and Automated Learning
Playing to learn: case-injected genetic algorithms for learning to play computer games

IEEE Transactions on Evolutionary Computation

Real-time team-mate AI in games: a definition, survey, & critique

Proceedings of the Fifth International Conference on the Foundations of Digital Games
Coevolving influence maps for spatial team tactics in a RTS game

Proceedings of the 12th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We evolve tactical control for entity groups in a naval real-time strategy game. Since tactical maneuvering involves spatial reasoning, our evolutionary algorithm evolves a set of influence maps that help specify an entity's spatial objectives. The entity then uses the A* route ?nding algorithm to generate waypoints according to the influence map, and follows them to achieve spatial objectives. Using this representation, our evolutionary algorithm quickly evolves increasingly better capture-the-flag tactics on three increasingly difficult maps. These preliminary results indicate (1) the usefulness of our particular influence map encoding for representing spatially resolved tactics and (2) the potential for using co-evolution to generate increasingly complex and competent tactics in our game. More generally, this work represents another step in our ongoing effort to investigate the co-evolution of competent game players in a real-time, continuous, environment that does not assume complete knowledge of the game state.