Error bound analysis of policy iteration based approximate dynamic programming for deterministic discrete-time nonlinear systems.
Wentao GuoFeng LiuJennie SiShengwei MeiRui LiPublished in: IJCNN (2015)
Keyphrases
- approximate dynamic programming
- nonlinear systems
- error bounds
- policy iteration
- linear program
- markov decision processes
- finite state
- fuzzy model
- reinforcement learning
- worst case
- fuzzy control
- dynamic programming
- adaptive control
- control law
- fuzzy systems
- fixed point
- machine learning
- theoretical analysis
- least squares
- artificial neural networks
- decision making
- learning algorithm