On-line Training of ESN and IP Tuning Effect
In the present paper we investigate influence of IP tuning of Echo state network (ESN) reservoir on the overall behavior of the on-line trained adaptive critic network. The experiments were done using Adaptive Critic Design (ACD) scheme with on-line trainable ESN critic for real time control of a mobile laboratory robot. Comparison of behavior of ESN critics trained with and without IP tuning showed that IP algorithm improved critic behavior significantly. It was observed that IP tuning prevents uncontrolled increase of reservoir output weights during on-line training.
KeywordsEcho state network RNN stability IP training of reservoir on-line training Recursive Least Squares
Unable to display preview. Download preview PDF.
- 1.Barabanov, N., Prokhorov, D.: Stability analysis of discrete-time recurrent neural networks. IEEE Trans. on Neural Networks 13(2), 292–303 (2002)Google Scholar
- 2.Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the echo state network approach. GMD Report 159, German National Research Center for Information Technology (2002)Google Scholar
- 3.Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: Advances in Neural Information Processing Systems 15 (NIPS 2002), pp. 593–600. MIT Press, Cambridge (2003)Google Scholar
- 4.Haddad, W.M., Chellaboina, V.S., Nersesov, S.G.: Thermodynamics: A Dynamical System Approach. Princeton University Press (2005)Google Scholar
- 7.Prokhorov, D.V.: Adaptive critic designs and their applications. Ph.D. dissertation. Department of Electrical Engineering, Texas Tech. Univ. (1997)Google Scholar