A model-free robust policy iteration algorithm for optimal control of nonlinear systems.
Shubhendu BhasinMarcus JohnsonWarren E. DixonPublished in: CDC (2010)
Keyphrases
- optimal control
- nonlinear systems
- model free
- control law
- policy iteration
- reinforcement learning
- policy iteration algorithm
- lyapunov function
- adaptive control
- infinite horizon
- control problems
- reinforcement learning algorithms
- actor critic
- hamilton jacobi bellman
- fuzzy control
- dynamic programming
- temporal difference
- lyapunov stability
- control strategy
- function approximation
- policy evaluation
- rl algorithms
- markov decision processes
- fuzzy model
- learning rate
- average reward
- fuzzy systems
- optimal policy
- learning algorithm
- tracking error
- approximate dynamic programming
- machine learning
- real time
- markov decision process
- linear matrix inequality
- least squares
- action selection
- learning problems
- convergence rate
- control algorithm