Abstract
We investigate an evolution model of adaptive self-learning agents. The control system of agents is based on a neural network adaptive critic design. Each agent is a broker that predicts stock price changes and uses its predictions for action selection. We analyzed different regimes of learning and evolution and demonstrated that 1) evolution and learning together are more effective in searching for the optimal agent policy than evolution alone or learning alone; 2) in some regimes the Baldwin effect (genetic assimilation of initially acquired adaptive learning features during the course of Darwinian evolution) is observed; 3) inertial switching between two behavioral tactics similar to searching adaptive behavior of simple animals takes place during initial stages of evolutionary processes.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ackley, D., Littman, M.: Interactions between Learning and Evolution. In: Langton, C.G., et al. (eds.) Artificial Life II, pp. 487–509. Addison-Wesley, Reading (1992)
Suzuki, R., Arita, T.: Interactions between Learning and Evolution: Outstanding Strategy Generated by the Baldwin Effect. Biosystems 77, 57–71 (2004)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Braun, H., Ragg, T.: Evolutionary Optimization of Neural Networks for Reinforcement Learning Algorithms. In: ICML 1996, Workshop Proceedings on Evolutionary Computing and Machine Learning, Italy, pp. 38–45 (1996)
Prokhorov, D., Puskorius, G., Feldkamp, L.: Dynamical Neural Networks for Control. In: Kolen, J., Kremer, S. (eds.) A Field Guide to Dynamical Recurrent Networks, pp. 23–78. IEEE Press, Los Alamitos (2001)
Moody, J., Wu, L., Liao, Y., Saffel, M.: Performance Function and Reinforcement Learning for Trading Systems and Portfolios. Journal of Forecasting 17, 441–470 (1998)
Baldwin, J.M.: A New Factor in Evolution. American Naturalist 30, 441–451 (1896)
Nepomnyashchikh, V.A.: Selection Behaviour in Caddis Fly Larvae. In: Pfeifer, R., et al. (eds.) From Animals to Animats 5: Proceedings of the Fifth International Conference of the Society for Adaptive Behavior, pp. 155–160. MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Red’ko, V.G., Mosalov, O.P., Prokhorov, D.V. (2005). Investigation of Evolving Populations of Adaptive Agents. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Biological Inspirations – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3696. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550822_53
Download citation
DOI: https://doi.org/10.1007/11550822_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28752-0
Online ISBN: 978-3-540-28754-4
eBook Packages: Computer ScienceComputer Science (R0)