Neuro-Optimal Control for Discrete Stochastic Processes via a Novel Policy Iteration Algorithm.
Mingming LiangDing WangDerong LiuPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2020)
Keyphrases
- optimal control
- stochastic processes
- policy iteration algorithm
- markov processes
- brownian motion
- reinforcement learning
- stochastic process
- actor critic
- infinite horizon
- policy iteration
- finite state
- random fields
- control problems
- probability distribution
- dynamic programming
- random variables
- neural network
- neuro fuzzy
- control strategy
- markov decision processes
- finite number
- fuzzy rules
- approximate dynamic programming
- conditional random fields
- markov random field