Ensemble Methods for Reinforcement Learning with Function Approximation.
Stefan FaußerFriedhelm SchwenkerPublished in: MCS (2011)
Keyphrases
- function approximation
- ensemble methods
- reinforcement learning
- prediction accuracy
- decision trees
- function approximators
- temporal difference
- machine learning methods
- benchmark datasets
- temporal difference learning
- model free
- radial basis function
- state space
- learning tasks
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- learning process
- neural network
- learning algorithm
- machine learning
- temporal difference methods
- control policy
- policy gradient
- td learning
- reward function
- feature subset
- differential evolution
- machine learning algorithms
- linear combination
- feature extraction