Abstract
This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double T-Maze navigation tasks, where the robot has to locate and “remember” the position of a reward-zone. The “learning” comes about without modifications of synapse strengths, but simply from internal network dynamics, as proposed by [12]. Neural controllers are evolved in simulation and in the simple case evaluated on a real robot. The evolved controllers are analyzed and the results obtained are discussed.
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
J. Blynel. Evolving reinforcement learning-like abilities for robots. In (to appear) Proceedings on the 5th International Conference on Evolvable Systems (ICES’03): From Biology to Hardware. Springer Verlag, Berlin, 2003.
J. Blynel and D. Floreano. Levels of dynamics and adaptive behaviour in evolutionary neural controllers. In Hallam et al. [4], pages 272–281.
W. J. Freeman. The physiology of perception. Scientific American, 264:78–85, 1991.
B. Hallam, D. Floreano, J. Hallam, G Hayes, and J-A Meyer, editors. From Animals to Animats 7: Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior. MIT Press-Bradford Books, Cambridge, MA, 2002.
N. Jakobi. Evolutionary robotics and the radical envelope-of-noise hypothesis. Adaptive Behavior, 6(2):325–368, 1997.
O. Miglino, H. H. Lund, and S. Nolfi. Evolving mobile robots in simulated and real environments. Artificial Life, 2(4):417–434, 1995.
R. Pfeifer and C. Scheier. Understanding Intelligence. MIT Press, Cambridge, MA, 1999.
J. Tani. Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26:421–436, 1996.
J. Tani and S. Nol.. Learning to perceive the world as articulated: An approach for hierarchical learning in sensory-motor systems. Neural Networks, 12(7–8):1131–1141, 1999.
E. Tuci, I. Harvey, and M. Quinn. Evolving integrated controllers for autonomous learning robots using dynamic neural networks. In Hallam et al. [4], pages 282–291.
B. Yamauchi and R. D. Beer. Integrating reactive, sequential, and learning behaviour using dynamical neural networks. In D. Cli., P. Husbands, J. Meyer, and S. W. Wilson, editors, From Animals to Animats III: Proceedings of the Third International Conference on Simulation of Adaptive Behavior, pages 382–391. MIT Press-Bradford Books, Cambridge, MA, 1994.
B. Yamauchi and R. D. Beer. Sequential behavior and learning in evolved dynamical neural networks. Adaptive Behavior, 2(3):219–246, 1994.
T. Ziemke and M. Thieme. Neuromodulation of reactive sensorimotor mappings as a short-term memory mechanism in delayed response tasks. (to appear) Adaptive Behavior, 10(3–4), 2003.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Blynel, J., Floreano, D. (2003). Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs. In: Cagnoni, S., et al. Applications of Evolutionary Computing. EvoWorkshops 2003. Lecture Notes in Computer Science, vol 2611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36605-9_54
Download citation
DOI: https://doi.org/10.1007/3-540-36605-9_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00976-4
Online ISBN: 978-3-540-36605-8
eBook Packages: Springer Book Archive