A model-free on-off iterative adaptive controller based on stochastic approximation.
Bongsu HahnKenn R. OldhamPublished in: ACC (2010)
Keyphrases
- model free
- stochastic approximation
- policy iteration
- adaptive controller
- reinforcement learning
- adaptive control
- temporal difference
- fuzzy rules
- function approximation
- temporal difference learning
- robot manipulators
- reinforcement learning algorithms
- single neuron
- monte carlo
- rl algorithms
- control law
- markov decision processes
- optimal policy
- average reward
- least squares
- machine learning
- state space
- fuzzy logic
- control method
- closed loop
- theoretical guarantees
- stochastic games
- markov random field