Abstract
Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network architectures inside an animat: one that controls their high level deliberative behaviours, such as the selection of sub-goals, and one that provides reactive and navigational capabilities. Animats using this model are evolved in novel and dynamic environments, on complex tasks requiring deliberative behaviours: tasks that cannot be solved by reactive mechanisms alone and which would traditionally have their solutions formulated in terms of search-based planning. Significantly, no a priori information is given to the animats, making explicit forward search through state transitions impossible. The complexity of the problem means that animats must first learn to solve sub-goals without receiving any reward. Animats are shown increasingly complex versions of the task, with the results demonstrating, for the first time, incremental neuro-evolutionary learning on such tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Tyrrell, T.: Computational Mechanisms for Action Selection. PhD thesis, University of Edinburgh (1993)
Benjamin, M.R.: Virtues and limitations of multifusion based action selection. In: Agents ’00: The Fourth International Conference on Intelligent Agents, pp. 23–24 (2000)
Payton, D.W., Rosenblatt, J.K., Keirsey, D.M.: Plan guided reaction. IEEE Trans. on Systems, Man, and Cybernetics 20(6), 1370–1382 (1990)
Koren, Y., Borenstein, J.: Potential field methods and their inherent limitations for mobile robot navigation. In: IEEE Int. Conf. on Robotics and Automation, 1991, pp. 1398–1404. IEEE Computer Society Press, Los Alamitos (1991)
Brooks, R.A.: A robust layered control system for a mobile robot. IEEE J. Robot. and Auto. 2(3), 14–23 (1986)
Yang, S.X., Meng, M.: An efficient neural network approach to dynamic robot motion planning. Neural Networks 13(2), 143–148 (2000)
Yang, S.X., Meng, M.: An efficient neural network method for real-time motion planning with safety consideration. Robotics and Autonomous Systems 32(2-3), 115–128 (2000)
Schultz, A.C.: Adapting the evaluation space to improve global learning. In: Belew, R., Booker, L. (eds.) Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 158–164. Morgan Kaufman, San Mateo (1991)
Hodgkin, A.L., Huxley, A.F.: A quantitative description of membrane current and its application to conduction and excitation in nerve. Journal of Physiology 116, 500–544 (1952)
Grossberg, S.: Nonlinear neural networks: Principles, mechanisms, and architectures. Neural Networks 1, 17–61 (1988)
Seipone, T., Bullinaria, J.A.: The evolution of minimal catastrophic forgetting in neural systems. In: Mahwah, N.J. (ed.) Twenty-Seventh Annual Conference of the Cognitive Science Society, pp. 1991–1996. Lawrence Erlbaum Associates, Mahwah (2005)
White, R.W.: Motivation reconsidered: The concept of competence. Psychological Review 66(5), 297–333 (1959)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Robinson, E., Ellis, T., Channon, A. (2007). Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds) Advances in Artificial Life. ECAL 2007. Lecture Notes in Computer Science(), vol 4648. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74913-4_35
Download citation
DOI: https://doi.org/10.1007/978-3-540-74913-4_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74912-7
Online ISBN: 978-3-540-74913-4
eBook Packages: Computer ScienceComputer Science (R0)