Constructing Complex NPC Behavior via Multi-Objective Neuroevolution
Item
- Title
- Description
- Creator
- Date
- Date Available
- Date Issued
- Identifier
- uri
- Abstract
- Language
- Subject
- Type
-
Constructing Complex NPC Behavior via Multi-Objective Neuroevolution
-
This is an Accepted Manuscript of an article published in Proceedings of the Fourth Artificial Intelligence and Interactive Digital
Entertainment Conference (AIIDE 2008), pp. 108-113, Stanford, California 2008.
-
Schrum, Jacob
-
Miikkulainen, Risto
-
2016-12-09
-
2016-12-09
-
2008
-
In Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2008), pp. 108-113, Stanford, California 2008.
-
https://collections.southwestern.edu/s/suscholar/item/220
-
It is difficult to discover effective behavior for NPCs automatically.
For instance, evolutionary methods can learn sophisticated
behaviors based on a single objective, but realistic
game playing requires different behaviors at different
times. Such complex behavior is difficult to achieve. What
is needed are multi-objective methods that reward different
behaviors separately, and allow them to be combined to produce
multi-modal behavior. While such methods exist, they
have not yet been applied to generating multi-modal behavior
for NPCs. This paper presents such an application: In a domain
with noisy evaluations and contradictory fitness objectives,
evolution based on a scalar fitness function is inferior to
multi-objective optimization. The multi-objective approach
produces agents that excel at the task and develop complex,
interesting behaviors.
-
English
-
Game Development
-
Multi-objective Optimization
-
Multi-Objective Neuroevolution
-
Complex NPC Behavior
-
Article
- Item sets