Finite-sample guarantees for Nash Q-learning with linear function approximation.
Pedro Cisneros-VelardeSanmi KoyejoPublished in: UAI (2023)
Keyphrases
- function approximation
- finite sample
- reinforcement learning
- function approximators
- sample size
- temporal difference learning
- statistical learning theory
- uniform convergence
- radial basis function
- learning tasks
- temporal difference
- nearest neighbor
- model free
- error bounds
- reinforcement learning algorithms
- machine learning
- sufficient conditions
- dynamic programming
- active learning
- support vector
- td learning