Adaptive Teams of Agents in the Legion II game (2006)
Author: Bobby Bryant
Many classes of cooperative multi-agent systems require a diversity of behavior among the agents in order to optimize their performance as a team in the system. Conventionally the control policies for the agents in such systems are programmed or trained so that individual agents are hard-coded to adopt specialized roles within a team.

However, customized collections of specialists can be brittle when they are not deployed in the optimal ratio for a context, when the context changes after they are deployed, or when individual specialists break down. Thus for many multi-agent tasks a useful alternative would be to deploy a collection of identical general-purpose agents that are able to organize themselves with a division of labor appropriate to the current context and number of agents in the team.

In this project we examine how neuroevolution can be used to train artificial neural networks to be used for the controllers for sets of identical agents in systems where diversity of behavior is required. At present we are working with autonomous agents in strategy games and simulated construction tasks for our application domains.

See movies of agents in the Legion II strategy game.
Bobby D. Bryant Ph.D. Alumni bdbryant [at] cse unr edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Exploiting Sensor Symmetries in Example-based Training for Intelligent Agents Bobby D. Bryant and Risto Miikkulainen In Sushil M. Louis and Graham Kendall, editors, Proceedings of the {IEEE} Symposium on Computatio... 2006

Evolving Visibly Intelligent Behavior for Embedded Game Agents Bobby D. Bryant PhD Thesis, Department of Computer Sciences, The University of Texas at Austin, 2006. Technical Repo... 2006

Neuroevolution for Adaptive Teams Bobby D. Bryant and Risto Miikkulainen In Proceedings of the 2003 Congress on Evolutionary Computation (CEC 2003), 2194-2201, Pisca... 2003

Evolving Stochastic Controller Networks for Intelligent Game Agents Bobby D. Bryant and Risto Miikkulainen In Proceedings of the 2006 Congress on Evolutionary Computation, Piscataway, NJ, 2006. IEEE. 2006

Computational Intelligence in Games Risto Miikkulainen, Bobby D. Bryant, Ryan Cornelius, Igor V. Karpov, Kenneth O. Stanley, and Chern H... In Gary Y. Yen and David B. Fogel, editors, Computational Intelligence: Principles and Practice<... 2006

Acquiring Visibly Intelligent Behavior with Example-Guided Neuroevolution Bobby D. Bryant and Risto Miikkulainen In Proceedings of the Twenty-Second National Conference on Artificial Intelligence, Menlo Par... 2007

IJCNN-2013 Tutorial on Evolution of Neural Networks Risto Miikkulainen To Appear In 2013. Tutorial slides.. 2013

ESP C++ The ESP package contains the source code for the Enforced Sup-Populations system written in C++. ESP is an extension t... 2000

ESP JAVA 1.1 The ESP package contains the source code for the Enforced Sup-Populations system written in Java. This package is a near... 2002