Multiobjective Optimization
Instead of finding a single optimal solution to any given problem, multiobjective methods aim at finding a Pareto-front, which represents all of the trade-offs between objectives within the domain. A human decision maker can then decide which of the available trade-offs works best. Our work in this area focuses on generating multi-modal behavior, as well as maintaining diversity using multiobjective approaches.
Jacob Schrum Ph.D. Alumni schrum2 [at] cs utexas edu
Evolving Multimodal Behavior Through Modular Multiobjective Neuroevolution 2014
Jacob Schrum, PhD Thesis, The University of Texas at Austin. Tech Report TR-14-07.
Evolving Multimodal Behavior With Modular Neural Networks in Ms. Pac-Man 2014
Jacob Schrum and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014), pp. 325--332, Vancouver, BC, Canada, July 2014. Best Paper: Digital Entertainment and Arts.
Effective Diversity Maintenance in Deceptive Domains 2013
Joel Lehman, Kenneth O. Stanley and Risto Miikkulainen, To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2013 2013.
Evolving Multimodal Networks for Multitask Games 2012
Jacob Schrum and Risto Miikkulainen, IEEE Transactions on Computational Intelligence and AI in Games, Vol. 4, 2 (2012), pp. 94--111. IEEE.
Evolving Multimodal Networks for Multitask Games 2011
Jacob Schrum and Risto Miikkulainen, In Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2011), pp. 102--109, Seoul, South Korea, September 2011. IEEE. (Best Paper Award).
Evolving Agent Behavior In Multiobjective Domains Using Fitness-Based Shaping 2010
Jacob Schrum and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2010), pp. 439--446, Portland, Oregon, July 2010.
Evolving Multi-modal Behavior in NPCs 2009
Jacob Schrum and Risto Miikkulainen, In IEEE Symposium on Computational Intelligence and Games (CIG 2009), pp. 325--332, Milan, Italy, September 2009. (Best Student Paper Award).
Constructing Complex NPC Behavior via Multi-Objective Neuroevolution 2008
Jacob Schrum and Risto Miikkulainen, In Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2008), pp. 108-113, Stanford, California 2008.
MARLEDA: Effective Distribution Estimation Through Markov Random Fields 2007
Matthew Alden, PhD Thesis, Department of Computer Sciences, the University of Texas at Austin. Also Technical Report AI07-349.
MM-NEAT Modular Multiobjective NEAT is a software framework in Java that builds on the basic principles of 2014

UT^2: Winning Botprize 2012 Entry The Botprize Competition is an annual competition to program bots that appear human-l... 2012

BREVE Monsters BREVE is a system for designing Artificial Life simulations available at http://spiderlan... 2010