Continuous-Time Distributed Policy Iteration for Multicontroller Nonlinear Systems.
Qinglai WeiHongyang LiXiong YangHaibo HePublished in: IEEE Trans. Cybern. (2021)
Keyphrases
- nonlinear systems
- policy iteration
- markov decision processes
- optimal control
- control law
- adaptive control
- fuzzy systems
- model free
- fuzzy model
- least squares
- fixed point
- reinforcement learning
- fuzzy control
- optimal policy
- learning rate
- state space
- fuzzy controller
- dynamical systems
- markov chain
- infinite horizon
- dynamic programming
- pattern recognition
- temporal difference
- markov decision process
- average reward
- approximate dynamic programming
- rough sets
- convergence rate
- neural network