Article citationsMore>>

Sutton, R.S. and Barto, A.G. (1998) Reinforcement Learning: An Introduction. In: Adaptive Computation and Machine Learning. The MIT Press, Cambridge, MA.
https://doi.org/10.1109/TNN.1998.712192

has been cited by the following article:

• TITLE: Stability Analysis of a Neurocontroller with Kalman Estimator for the Inverted Pendulum Case

  AUTHORS: Julián Antonio Pucheta, Cristian Rodríguez Rivero, Carlos Alberto Salas, Martín Herrera, Sergio Oscar Laboret

  KEYWORDS: Optimal Control, Neurocontroller, Inverted Pendulum, State Estimation, Stability

  JOURNAL NAME: Applied Mathematics, Vol.8 No.11, November 24, 2017

  ABSTRACT: In this paper, a practical analysis of stability by simulation for the effect of incorporating a Kalman estimator in the control loop of the inverted pendulum with a neurocontroller is presented. The neurocontroller is calculated by approximate optimal control, without considering the Kalman estimator in the loop following the Theorem of the separation. The results are compared with a time-varying linear controller, which in noiseless conditions in the state or in the measurement has an acceptable performance, but when it is under noise conditions its operation closes into a state space range more limited than the one proposed here.