Abstract
Presented topic is from the research field called Artificial Life, but contributes also to the field of Artificial Intelligence (AI), Robotics and potentially into many other aspects of research. In this paper, there is reviewed and tested new approach to autonomous design of agent architectures. This novel approach is inspired by inherited modularity of biological brains. During designing of new brains, the evolution is not directly connecting individual neurons. Rather than that, it composes new brains by connecting larger, widely reused areas (modules). In this approach, agent architectures are represented as hybrid artificial neural networks composed of heterogeneous modules. Each module can implement different selected algorithm. Rather than describing this framework, this paper focuses on designing of one module. Such a module represents one component of hybrid neural network and can seamlessly integrate a selected algorithm into the node. The course of design of such a module is described on example of discrete reinforcement learning algorithm. The requirements posed by the framework are presented, the modifications on the classical version of algorithm are mentioned and then the resulting performance of module with expectations is evaluated. Finally, the future use cases of this module are described.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
University of Waterloo, Simulator of large-scale ANNs Nengo: nengo.ca
- 2.
Robotic Operating System http://www.ros.org/
- 3.
Nengoros: http://nengoros.wordpress.com/
- 4.
Picture borrowed from: http://www.tu-chemnitz.de/informatik/KI/scripts/
- 5.
With the BenchMark simulator available at: https://github.com/jvitku/rl
References
Auda, G., Kamel, M.: Modular neural networks: a survey. Int. J. Neural Syst. 9(2), 129–151 (1999)
Deb, K.: Multi-objective optimisation using evolutionary algorithms: an introduction. In: Wang, L., Ng, A.H.C., Deb, K. (eds.) Multi-objective Evolutionary Optimisation for Product Design and Manufacturing, pp. 3–34. Springer, London (2011)
Gu, D., Hu, H.: Reinforcement learning of fuzzy logic controllers for quadruped walking robots (2002)
Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw. 14, 1569–1572 (2003)
Kadlecek, D.: Motivation driven reinforcement learning and automatic creation of behavior hierarchies. PhD thesis, Czech Technical University in Prague, Faculty of Electrical Engineering (2008)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. J. Neural Netw. 10, 1659–1671 (1996)
Murre, J.M.J., Phaf, R.H., Wolters, G.: Calm networks: a modular approach to supervised and unsupervised learning. In: Proceedings of International Joint Conference on Neural Networks, IJCNN, pp. 649–656 (1989)
Thomas, D.B., Luk, W.: FPGA accelerated simulation of biologically plausible spiking neural networks. In: Proceedings of the IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM), April 2009
Vitku, J.: An artificial creature capable of learning from experience in order to fulfill more complex tasks. Diploma thesis, Czech Technical University in Prague, Faculty of Electrical Engineering, Department of Cybernetics (2011). Supervisor: Doc. Ing. Nahodil Pavel CSc. (in English)
Acknowledgments
This research has been funded by the Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, partially under the following SGS Projects SGS12/146/OHK3/2T/13 and OHK3-013/14.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Vítků, J., Nahodil, P. (2014). Q-Learning Algorithm Module in Hybrid Artificial Neural Network Systems. In: Silhavy, R., Senkerik, R., Oplatkova, Z., Silhavy, P., Prokopova, Z. (eds) Modern Trends and Techniques in Computer Science. Advances in Intelligent Systems and Computing, vol 285. Springer, Cham. https://doi.org/10.1007/978-3-319-06740-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-06740-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06739-1
Online ISBN: 978-3-319-06740-7
eBook Packages: EngineeringEngineering (R0)