Reinforcement Learning with Linear Function Approximation and LQ control Converges
Istvan SzitaAndrás LörinczPublished in: CoRR (2003)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- optimal control
- control problems
- temporal difference
- temporal difference learning
- control policy
- model free
- policy search methods
- control system
- adaptive control
- mountain car
- learning tasks
- radial basis function
- state space
- control strategies
- optimal policy
- temporal difference methods
- multi agent
- machine learning
- reinforcement learning algorithms
- artificial neural networks
- reinforcement learning problems
- nonlinear systems
- text classification
- feedback control
- inverted pendulum
- feature space
- reinforcement learning methods