Reinforcement learning with reference tracking control in continuous state spaces.
Joseph HallCarl Edward RasmussenJan M. MaciejowskiPublished in: CDC/ECC (2011)
Keyphrases
- tracking control
- continuous state spaces
- reinforcement learning
- state space
- continuous state
- nonlinear systems
- action space
- control problems
- control law
- markov decision processes
- adaptive control
- rl algorithms
- adaptive neural
- model free
- dynamical systems
- closed loop
- optimal policy
- fuzzy model
- function approximation
- dynamic programming
- partially observable markov decision processes
- control policies
- control system
- fuzzy controller
- planning problems
- learning problems
- fuzzy control
- state action
- markov decision problems
- markov decision process
- partially observable
- reinforcement learning algorithms
- real time
- optimal control
- supervised learning
- learning algorithm
- machine learning