A Dantzig Selector Approach to Temporal Difference Learning.
Matthieu GeistBruno ScherrerAlessandro LazaricMohammad GhavamzadehPublished in: ICML (2012)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- reinforcement learning
- game playing
- evaluation function
- temporal difference
- approximate value iteration
- reinforcement learning algorithms
- markov decision process
- learning experience
- model free
- policy iteration
- artificial neural networks
- bayesian networks
- function approximators
- training set