Properties of the Least Squares Temporal Difference learning algorithm
Kamil CiosekPublished in: CoRR (2013)
Keyphrases
- temporal difference
- least squares
- policy evaluation
- reinforcement learning
- learning algorithm
- reinforcement learning algorithms
- td learning
- evaluation function
- policy iteration
- function approximation
- monte carlo
- temporal difference learning
- supervised learning
- model free
- training data
- machine learning algorithms
- temporal difference methods
- action selection
- state space
- markov decision processes
- text classification
- active learning
- genetic algorithm