Model-based function approximation in reinforcement learning.
Nicholas K. JongPeter StonePublished in: AAMAS (2007)
Keyphrases
- function approximation
- reinforcement learning
- model free
- temporal difference
- tile coding
- function approximators
- reinforcement learning algorithms
- mountain car
- state action space
- temporal difference learning
- radial basis function
- learning tasks
- temporal difference learning algorithms
- learning algorithm
- control problems
- policy iteration
- machine learning
- temporal difference methods
- multi agent
- state space
- multi label
- policy evaluation
- optimal policy
- markov decision processes
- active learning
- learning process
- supervised learning
- text classification
- monte carlo
- data mining