A reinforcement learning neural network for adaptive control of Markov chains.
G. SantharamP. S. SastryPublished in: IEEE Trans. Syst. Man Cybern. Part A (1997)
Keyphrases
- adaptive control
- markov chain
- reinforcement learning
- neural network
- state space
- feedback control
- steady state
- finite state
- control problems
- nonlinear systems
- transition probabilities
- markov process
- random walk
- stochastic process
- function approximation
- neural network model
- markov processes
- markov model
- optimal policy
- adaptive controller
- monte carlo
- control method
- back propagation
- variable structure
- markov decision processes
- dynamic environments
- model free
- genetic algorithm
- optimal control
- chaotic systems
- dynamic programming
- transition matrix
- probabilistic automata
- fuzzy systems
- stationary distribution
- fuzzy logic
- learning algorithm
- control law
- machine learning
- markov decision process
- state variables
- bp neural network
- dynamical systems
- random numbers