David Shorten
ABSTRACT
We present ongoing research that is an extension of novelty search, flood evolution. This technique aims to improve evolutionary algorithms by presenting them with large sets of problems, as opposed to individual ones. If the older approach of incremental evolution were analogous to moving over a path of stepping stones, then this approach is similar to navigating a rocky field. The method is discussed and preliminary results are presented.
- W. B. Arthur and W. Polak. The evolution of technology within a simple computer model. Complexity, 11(5):23--31, 2006. Google Scholar
Digital Library
- J. W. O. Ballard and M. C. Whitlock. The incomplete natural history of mitochondria. Molecular ecology, 13(4):729--744, 2004.Google ScholarCross Ref
- C. Darwin and W. F. Bynum. The origin of species by means of natural selection: or, the preservation of favored races in the struggle for life. AL Burt, 2009.Google Scholar
- R. Dawkins. The selfish gene. Oxford university press, 2006.Google Scholar
- A. E. Eiben and J. E. Smith. Introduction to evolutionary computing. springer, 2003. Google ScholarDigital Library
- F. Gomez and R. Miikkulainen. Incremental evolution of complex general behavior. Adaptive Behavior, 5(3-4):317--342, 1997. Google ScholarDigital Library
- F. J. Gomez and R. Miikkulainen. Solving non-markovian control tasks with neuroevolution. In IJCAI, volume 99, pages 1356--1361, 1999. Google ScholarDigital Library
- C. Y. Lee. An algorithm for path connections and its applications. Electronic Computers, IRE Transactions on, (3):346--365, 1961.Google Scholar
- J. Lehman and K. O. Stanley. Exploiting open-endedness to solve problems through the search for novelty. In Proceedings of the Eleventh International Conference on Artificial Life (ALIFE XI), Cambridge, MA, 2008. MIT Press.Google Scholar
- J. Lehman and K. O. Stanley. Abandoning objectives: Evolution through the search for novelty alone. Evolutionary computation, 19(2):189--223, 2011. Google ScholarDigital Library
- J. Lehman and K. O. Stanley. Evolving a diversity of virtual creatures through novelty search and local competition. In Proceedings of the 13th annual conference on Genetic and evolutionary computation, pages 211--218. ACM, 2011. Google ScholarDigital Library
- R. E. Lenski, C. Ofria, R. T. Pennock, and C. Adami. The evolutionary origin of complex features. Nature, 423(6936):139--144, 2003.Google ScholarCross Ref
- M. Lynch. The frailty of adaptive hypotheses for the origins of organismal complexity. Proceedings of the National Academy of Sciences, 104(suppl 1):8597--8604, 2007.Google ScholarCross Ref
- S. Risi, C. E. Hughes, and K. O. Stanley. Evolving plastic neural networks with novelty search. Adaptive Behavior, 18(6):470--491, 2010. Google ScholarDigital Library
- N. Saravanan and D. B. Fogel. Evolving neural control systems. IEEE Intelligent Systems, 10(3):23--27, 1995. Google ScholarDigital Library
- A. P. Wieland. Evolving controls for unstable systems. In Connectionist models: proceedings of the 1990 summer school, pages 91--102, 1990.Google Scholar
- A. P. Wieland. Evolving neural network controllers for unstable systems. In Neural Networks, 1991, IJCNN-91-Seattle International Joint Conference on, volume 2, pages 667--673. IEEE, 1991.Google ScholarCross Ref
- J. J. Wiens. Missing data, incomplete taxa, and phylogenetic accuracy. Systematic Biology, 52(4):528--538, 2003.Google ScholarCross Ref
- J. Xu and C. S. Kaplan. Image-guided maze construction. In ACM Transactions on Graphics (TOG), volume 26, page 29. ACM, 2007. Google ScholarDigital Library
- C. H. Yong and R. Miikkulainen. Coevolution of role-based cooperation in multiagent systems. Autonomous Mental Development, IEEE Transactions on, 1(3):170--186, 2009. Google ScholarDigital Library
Index Terms
- Flood evolution: changing the evolutionary substrate from a path of stepping stones to a field of rocks
Recommendations
An examination of different fitness and novelty based selection methods for the evolution of neural networks
It has been suggested recently that it is a reasonable abstraction of evolutionary processes to use evolutionary algorithms that select individuals based on the novelty of their behavior instead of their fitness. Here we study the performance of fitness-...
Open-ended evolution with multi-containers QD
GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference CompanionEvolution in nature has allowed biological systems to develop and survive in many different environments. It can be attributed to one of the major features of natural evolution: its open-endedness, that can be considered as the ability to continuously ...
Minimal criterion coevolution: a new approach to open-ended search
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceRecent studies have emphasized the merits of search processes that lack overarching objectives, instead promoting divergence by rewarding behavioral novelty. While this less objective search paradigm is more open-ended and divergent, it still differs ...
Comments