Online model-free controller for flexible wing aircraft: a policy iteration-based reinforcement learning approach.
Mohammed I. AbouheafWail GueaiebPublished in: Int. J. Intell. Robotics Appl. (2020)
Keyphrases
- model free
- policy iteration
- reinforcement learning
- impedance control
- actor critic
- policy iteration algorithm
- reinforcement learning algorithms
- markov decision processes
- function approximation
- policy evaluation
- temporal difference
- average reward
- optimal control
- adaptive control
- temporal difference learning
- control system
- state space
- reinforcement learning methods
- fixed point
- optimal policy
- markov decision problems
- least squares
- markov decision process
- rl algorithms
- multi agent
- partially observable
- machine learning
- supervised learning
- learning problems
- linear programming