TY - GEN
T1 - Robust player imitation using multiobjective evolution
AU - Van Hoorn, Niels
AU - Togelius, Julian
AU - Wierstra, Daan
AU - Schmidhuber, Jürgen
PY - 2009
Y1 - 2009
N2 - The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.
AB - The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.
UR - http://www.scopus.com/inward/record.url?scp=70449890193&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70449890193&partnerID=8YFLogxK
U2 - 10.1109/CEC.2009.4983007
DO - 10.1109/CEC.2009.4983007
M3 - Conference contribution
AN - SCOPUS:70449890193
SN - 9781424429592
T3 - 2009 IEEE Congress on Evolutionary Computation, CEC 2009
SP - 652
EP - 659
BT - 2009 IEEE Congress on Evolutionary Computation, CEC 2009
T2 - 2009 IEEE Congress on Evolutionary Computation, CEC 2009
Y2 - 18 May 2009 through 21 May 2009
ER -