Multivariate Decision Tree Function Approximation for Reinforcement Learning.
Hossein Bashashati SaghezchiMasoud AsadpourPublished in: ICONIP (1) (2010)
Keyphrases
- function approximation
- reinforcement learning
- decision trees
- temporal difference
- state action space
- function approximators
- mountain car
- machine learning
- reinforcement learning algorithms
- machine learning algorithms
- temporal difference learning
- tile coding
- model free
- learning algorithm
- radial basis function
- temporal difference learning algorithms
- td learning
- state space
- dynamic programming
- learning tasks
- training set
- support vector
- reinforcement learning methods
- temporal difference methods
- data mining
- control problems
- continuous state
- multi agent
- action selection
- learning problems
- knn