TY - GEN
T1 - Generating diverse opponents with multiobjective evolution
AU - Agapitos, Alexandros
AU - Togelius, Julian
AU - Lucas, Simon M.
AU - Schmidhuber, Jürgen
AU - Konstantinidis, Andreas
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 2008/12/1
Y1 - 2008/12/1
N2 - For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers. ©2008 IEEE.
AB - For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers. ©2008 IEEE.
UR - http://ieeexplore.ieee.org/document/5035632/
UR - http://www.scopus.com/inward/record.url?scp=70349300413&partnerID=8YFLogxK
U2 - 10.1109/CIG.2008.5035632
DO - 10.1109/CIG.2008.5035632
M3 - Conference contribution
SN - 9781424429745
SP - 135
EP - 142
BT - 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
ER -