Policy Approximation in Policy Iteration Approximate Dynamic Programming for Discrete-Time Nonlinear Systems.
Wentao GuoJennie SiFeng LiuShengwei MeiPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- approximate dynamic programming
- nonlinear systems
- policy iteration
- markov decision processes
- finite state
- optimal policy
- dead zone
- reinforcement learning
- adaptive control
- model free
- fixed point
- markov decision process
- fuzzy control
- learning rate
- least squares
- actor critic
- markov chain
- average reward
- fuzzy model
- control law
- markov decision problems
- convergence rate
- infinite horizon
- state space
- temporal difference
- fuzzy controller
- function approximation
- optimal control
- queueing networks
- average cost
- linear program
- linear programming
- dynamic programming
- neural network
- monte carlo
- data mining
- particle swarm optimization
- partially observable
- supervised learning
- approximation methods
- control policy
- control system
- artificial neural networks
- decision making
- machine learning