Abstract
We have developed a new efficient neural network-based algorithm for Alife application in a competitive world whereby the effects of interactions between organisms are evaluated in a weak form by exploiting the position of nearest food elements into consideration but not the positions of the other competing organisms. Two online learning algorithms, an instructive ASL (adaptive supervised learning) and an evaluative feedback-oriented RL (reinforcement learning) algorithm developed have been tested in simulating Alife environments with various neural network algorithms. Adopting an adaptively selected best sequence of feedback action period Δα which we have found to be a decisive parameter in improving the network efficiency, the ASL-guided FuzGa had an improved performance as compared with ASL-guided CasCor and RL-guided FuzGa. We confirm that the present solution successfully evaluates the effect of interactions at a larger F A(food availability), reducing to an isolated solution at a lower value of F A.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
F. Dellaert and R. Beer, “Toward an Evolvable Model of Development for Autonomous Agent Synthesis”, Artificial Life IV, The MIT Press, pp.246–257, 1996.
B. Fullmer and R. Miikkulainen, “Using Marker-Based Genetic Encoding of Neural Networks to Evolve Finite-State Behaviour”, Proc. 1st European Conference on Artificial Life, Paris, 1991.
L. Kaelbling, M. Littman and A. Moore, “Reinforcement learning: A survey”, Journal of Artificial Intelligence Research, Vol.4, pp.237–285, 1996.
H. Lund, “Specialization under social conditions in competitive environments”, Proc. 3rd European Conference on Artificial Life, Spain, 1995.
S. Nolfi and D. Parisi, “Auto-teaching: networks that develop their own teaching input”, Proc. 2nd European Conference on Artificial Life, Brussels, 1993.
J. Yan, N. Tokuda and J. Miyamichi, “A New Constructive Compound Neural Networks Using Fuzzy Logic and Genetic Algorithm: 1 Application to Artificial Life”, IEICE Transactions on Information and Systems, Vol. E81-D, No.12, pp. 1507–1516, Dec. 1998.
S. Fahlman and C. Libiere, “The Cascade-Correlation Learning Architecture”, D. Touretzky, ed., Advances in Neural Information Processing Systems II, Morgan Kaufmann, San Mateo, Calif., pp. 524–532, 1990.
V. Vysniauskas, F. Groen and B. Krose, “The optimal number of learning samples and hidden units in function approximation with a feedforward network”, Technical Report CS-93-15, University of Amsterdam, 1993.
C. Langton, ed., Artificial Life II, Addison-Wesley, MA, USA, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yan, J., Tokuda, N., Miyamichi, J. (2000). Simulating Competing Alife Organisms by Constructive Compound Neural Networks. In: Hamilton, H.J. (eds) Advances in Artificial Intelligence. Canadian AI 2000. Lecture Notes in Computer Science(), vol 1822. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45486-1_22
Download citation
DOI: https://doi.org/10.1007/3-540-45486-1_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67557-0
Online ISBN: 978-3-540-45486-1
eBook Packages: Springer Book Archive