Computer Science – Artificial Intelligence
Scientific paper
2011-06-30
Journal Of Artificial Intelligence Research, Volume 21, pages 63-100, 2004
Computer Science
Artificial Intelligence
Scientific paper
10.1613/jair.1338
Two major goals in machine learning are the discovery and improvement of solutions to complex problems. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for studying complexification. When compared to the evolution of networks with fixed structure, complexifying evolution discovers significantly more sophisticated strategies. The results suggest that in order to discover and improve complex solutions, evolution, and search in general, should be allowed to complexify as well as optimize.
Miikkulainen R.
Stanley K. O.
No associations
LandOfFree
Competitive Coevolution through Evolutionary Complexification does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Competitive Coevolution through Evolutionary Complexification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Competitive Coevolution through Evolutionary Complexification will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-479987