A new convergent variant of Q-learning with linear function approximation.
Diogo CarvalhoFrancisco S. MeloPedro SantosPublished in: NeurIPS (2020)
Keyphrases
- function approximation
- temporal difference learning algorithms
- reinforcement learning
- function approximators
- tile coding
- state action space
- temporal difference
- radial basis function
- temporal difference learning
- learning tasks
- model free
- td learning
- reinforcement learning algorithms
- reinforcement learning problems
- least squares
- real valued
- pattern recognition
- mountain car
- machine learning