Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation.
Pedro Cisneros-VelardeSanmi KoyejoPublished in: CoRR (2023)
Keyphrases
- function approximation
- finite sample
- reinforcement learning
- sample size
- function approximators
- uniform convergence
- statistical learning theory
- temporal difference learning
- learning tasks
- radial basis function
- nearest neighbor
- model free
- error bounds
- temporal difference
- td learning
- reinforcement learning algorithms
- sufficient conditions
- state space
- high dimensional
- pattern recognition