Abstract
In this paper we present a strategy for inducing a behavior in a real agent through a learning process with a human teacher. The agent creates internal models extracting information from the consequences of the actions it must carry out, and not just learning the task itself. The mechanism that permits this background learning process is the Multilevel Darwinist Brain, a cognitive mechanism that allows an autonomous agent to decide the actions it must apply in its environment in order to fulfill its motivations. It is a reinforcement based mechanism that uses evolutionary techniques to perform the on line learning of the models.
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
Weng, J., Zhang, Y.: Developmental Robots - A New Paradigm. In: Proceedings Second International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, vol. 94, pp. 163–174 (2003)
Bakker, P., Kuniyoshi, Y.: Robot see, robot do: An overview of robot imitation, Autonomous Systems Section, Electrotechnical Laboratory. Tsukuba Science City, Japan (1996)
Voylesl, R., Khosla, P.: A multi-agent system for programming robotic agents by human demonstration. In: Proc. AI and Manufacturing Research Planning Workshop (1998)
Lauria, S., Bugmann, G., Kyriacou, T., Klein, E.: Mobile robot programming using natural language. Robotics and Autonomous Systems 38, 171–181 (2002)
Nicolescu, M., Mataric, M.J.: Natural Methods for Robot Task Learning: Instructive Demonstration, Generalization and Practice. In: Proceedings, Second International Joint Conference on Autonomous Agents and Multi-Agent Systems, pp. 241–248 (2003)
Schaal, S.: Learning from demonstration. Advances in Neural Information Processing Systems 9, 1040–1046 (1997)
Ullerstam, M.: Teaching Robots Behavior Patterns by Using Reinforcement Learning– How to Raise Pet Robots with a Remote Control, Master’s Thesis in Computer Science at the School of Computer Science and Engineering, Royal Institute of Technology (2004)
Asada, M., MacDorman, K.F., Ishiguro, H., Kuniyoshi, Y.: Cognitive Developmental Robotics As a New Paradigm for the Design of Humanoid Robots. Robotics and Autonomous System 37, 185–193 (2001)
Changeux, J., Courrege, P., Danchin, A.: A Theory of the Epigenesis of Neural Networks by Selective Stabilization of Synapses. Proc.Nat. Acad. Sci. USA 70, 2974–2978 (1973)
Conrad, M.: Evolutionary Learning Circuits. Theor. Biol. 46, 167–188 (1974)
Edelman, G.: Neural Darwinism. The Theory of Neuronal Group Selection. Basic Books, New York (1987)
Bellas, F., Duro, R.J.: Multilevel Darwinist Brain in Robots: Initial Implementation. In: ICINCO 2004 Proceedings Book, vol. 2, pp. 25–32 (2004)
Bellas, F., Duro, R.J.: Introducing long term memory in an ann based multilevel darwinist brain, Computational methods in neural modeling, pp. 590–598. Springer, Heidelberg (2003)
Bellas, F., Duro, R.J.: Statistically neutral promoter based GA for evolution with dynamic fitness functions. In: Proceedings of the 2nd iasted international conference, pp. 335–340 (2002)
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
Bellas, F., Becerra, J.A., Duro, R.J. (2005). Induced Behavior in a Real Agent Using the Multilevel Darwinist Brain. In: Mira, J., Álvarez, J.R. (eds) Artificial Intelligence and Knowledge Engineering Applications: A Bioinspired Approach. IWINAC 2005. Lecture Notes in Computer Science, vol 3562. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11499305_44
Download citation
DOI: https://doi.org/10.1007/11499305_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26319-7
Online ISBN: 978-3-540-31673-2
eBook Packages: Computer ScienceComputer Science (R0)