Model-free Approximate Dynamic Programming Schemes for Linear Systems.
Asma Al-TamimiDraguna L. VrabieMurad Abu-KhalafFrank L. LewisPublished in: IJCNN (2007)
Keyphrases
- model free
- approximate dynamic programming
- linear systems
- policy iteration
- reinforcement learning
- sufficient conditions
- function approximation
- dynamical systems
- reinforcement learning algorithms
- temporal difference
- linear program
- sparse linear systems
- dynamic programming
- state space
- markov decision processes
- control policy
- markov decision problems
- optimal policy
- search space
- machine learning
- neural network