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.
People
Olivier Francon Collaborator olivier francon [at] cognizant com
Jacob Schrum Ph.D. Alumni schrum2 [at] southwestern edu
Cem C Tutum Formerly affiliated Research Scientist tutum [at] cs utexas edu
Publications
     [Expand to show all 19][Minimize]
Neuroevolution 2022
Risto Miikkulainen, To Appear In Encyclopedia of Machine Learning and Data Science, 3rd Edition, Dinh Phung, Claude Sammut and Geoffrey I. Webb (Eds.), New York, 2022. Springer.
Generalization of Agent Behavior through Explicit Representation of Context 2021
Cem Tutum, Suhaib Abdulquddos, Risto Miikkulainen, In Proceedings of the 3rd IEEE Conference on Games, , 2021.
Adapting to Unseen Environments through Explicit Representation of Context 2020
Cem C Tutum, Risto Miikkulainen, In Proceedings of the 2020 Conference on Artificial Life (ALIFE 2020), pp. 581--588, Montreal, Canada, July 2020. The MIT Press.
Enhanced Optimization with Composite Objectives and Novelty Selection 2018
Hormoz Shahrzad, Daniel Fink and Risto Miikkulainen, In Proceedings of the 2018 Conference on Artificial Life, Tokyo, Japan 2018.
Evolutionary Neural Architecture Search for Deep Learning 2018
Jason Zhi Liang, PhD Thesis, The University of Texas at Austin.
Discovering Evolutionary Stepping Stones through Behavior Domination 2017
Elliot Meyerson and Risto Miikkulainen, To Appear In Proceedings of The Genetic and Evolutionary Computation Conference (GECCO 2017), Berlin, Germany, July 2017. ACM.
Evolutionary Decomposition for 3D Printing 2017
Eric A. Yu, Jin Yeom, Cem C. Tutum, Etienne Vouga, Risto Miikkulainen, To Appear In Proceedings of The Genetic and Evolutionary Computation Conference (GECCO 2017) (Best Paper Award), pp. 8 pages, Berlin, Germany, July 2017.
Discovering Multimodal Behavior in Ms. Pac-Man through Evolution of Modular Neural Networks 2016
Jacob Schrum and Risto Miikkulainen, IEEE Transactions on Computational Intelligence and AI in Games, Vol. 8, 1 (2016), pp. 67--81.
Neuroevolution 2015
Risto Miikkulainen, In Encyclopedia of Machine Learning, 2nd Edition, Sammut, C. and Webb, G. I. (Eds.), Berlin, 2015. Springer.
Solving Interleaved and Blended Sequential Decision-Making Problems through Modular Neuroevolution 2015
Jacob Schrum and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015), pp. 345--352, Madrid, Spain, July 2015. Best Paper: Digital Entertainment and Arts.
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.
Projects
The Role of Emotion and Communication in Cooperative Behavior 2013 - 2016
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2014
Software/Data
MM-NEAT Download at GitHub

Modular Multiobjective NEAT is a software fra... 		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
Demos
Multimodal Behavior in Isolated Ms. Pac-ManJacob Schrum2015
Multimodal Behavior in Imprison Ms. Pac-ManJacob Schrum2014
Multimodal Behavior in One Life Ms. Pac-ManJacob Schrum2014
Multimodal Behavior in Multiple Lives Ms. Pac-ManJacob Schrum2014
UT^2: Winner of 2012 BotPrize in Unreal Tournament 2004Jacob Schrum, Igor Karpov2012
Multi-modal Approaches to Evolving Behavior for Multi-task GamesJacob Schrum2011
Fitness-based Shaping in Multi-objective DomainsJacob Schrum2010
Multi-modal Behavior in NPCsJacob Schrum2009
Multi-objective Neuroevolution of NPCsJacob Schrum2008
Labs
Neural Networks