Two steps reinforcement learning.
Fernando FernándezDaniel BorrajoPublished in: Int. J. Intell. Syst. (2008)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- control problems
- learning algorithm
- temporal difference
- optimal policy
- reinforcement learning algorithms
- databases
- multi step
- model free
- markov decision processes
- machine learning
- dynamic programming
- expert systems
- learning problems
- data structure
- multiscale
- feature selection
- information systems
- real time