neural networks research group
areas • people • projects • demos • publications • software/data •
Jacob Schrum
Ph.D. Student
Jacob is interested in automatic discovery of complex multi-modal behavior, particularly in the domain of real-time games. Agents that can behave in different manners in response to different situations are crucial for games because human players adapt so quickly. If a game's NPCs can learn multiple different behaviors to respond to humans' adaptive behavior, then the game is more challenging and more fun.
Homepage:
http://www.cs.utexas.edu/~schrum2/
Projects
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2012
Human-like Bots in Unreal Tournament 2008 - 2012
Constructing Intelligent Agents in Simulated Worlds 2008 - 2010
Demos
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
Publications (9)
Believable Bot Navigation via Playback of Human Traces Igor V. Karpov, Jacob Schrum, Risto Miikkulainen In Philip F. Hingston, editors, Believable Bots, 151--170, 2012. Springer Berlin Heidelberg. 2012
Evolving Multimodal Networks for Multitask Games Jacob Schrum and Risto Miikkulainen Simon M. Lucas, editors, IEEE Transactions on Computational Intelligence and AI in Games, 4(2... 2012
Humanlike Combat Behavior via Multiobjective Neuroevolution Jacob Schrum, Igor V. Karpov and Risto Miikkulainen In Philip F. Hingston, editors, Believable Bots, 119--150, 2012. Springer Berlin Heidelberg. 2012
Evolving Multimodal Networks for Multitask Games Jacob Schrum and Risto Miikkulainen In Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2011), 102... 2011
UT^2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces Jacob Schrum, Igor V. Karpov and Risto Miikkulainen In Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2011), 329... 2011
Evolving Agent Behavior In Multiobjective Domains Using Fitness-Based Shaping Jacob Schrum and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2010), 439--446,... 2010
Evolving Multi-modal Behavior in NPCs Jacob Schrum and Risto Miikkulainen In IEEE Symposium on Computational Intelligence and Games (CIG 2009), 325--332, Milan, Italy,... 2009
Competition Between Reinforcement Learning Methods in a Predator-Prey Grid World Jacob Schrum Technical Report AI08-9, The University of Texas at Austin, Department of Computer Sciences, Novembe... 2008
Constructing Complex NPC Behavior via Multi-Objective Neuroevolution Jacob Schrum and Risto Miikkulainen In Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Confer... 2008
Software/Data
UT^2: Winning Botprize 2012 Entry The Botprize Competition is an annual competition to program bots that appear human-l... 2012
Areas of Interest
Multiagent Systems Evolutionary Computation Neuroevolution Multiobjective Optimization Reinforcement Learning Game Playing
UT Only: Wiki • Calendar • Admin