Towards the evolutionary emergence of increasingly complex advantageous behaviours

作者: A. D. Channon , R. I. Damper

DOI: 10.1080/002077200406570

关键词:

摘要: The generation of complex entities with advantageous behaviours beyond our manual design capability requires long-term incremental evolution continuing emergence. In this paper, we argue that artificial selection models, such as traditional genetic algorithms, are fundamentally inadequate for goal. Existing natural systems evaluated, revealing both significant achievements and pitfalls. Thus, some requirements the perpetuation evolutionary emergence established. An (artificial) environment containing simple virtual autonomous organisms neural controllers has been created to satisfy these aid in development an accompanying theory Resulting reported alongside their correlates. a particular example, collective behaviour one species provides selective force which is overcome by another species, demonstrating via natura...

参考文章(40)
J. SKIPPER, THE COMPUTER ZOO – EVOLUTION IN A BOX Advances in Fuzzy Systems — Applications and Theory. pp. 151- 173 ,(1998) , 10.1142/9789812816153_0006
Rudy Rucker, Artificial Life Lab ,(1993)
Stewart W. Wilson, The animat path to AI simulation of adaptive behavior. pp. 15- 21 ,(1991)
R. I. Damper, A. D. Channon, Evolving novel behaviors via natural selection Bradford Books/MIT Press. ,(1998)
Achim Stephan, Varieties of Emergence in Artificial and Natural Systems Zeitschrift für Naturforschung C. ,vol. 53, pp. 639- 656 ,(1998) , 10.1515/ZNC-1998-7-817
Phil Husbands, Dave Cliff, Inman Harvey, Incremental evolution of neural network architectures for adaptive behavior. the european symposium on artificial neural networks. ,(1993)
Dave Cliff, Geoffrey F. Miller, Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations european conference on artificial life. pp. 200- 218 ,(1995) , 10.1007/3-540-59496-5_300