Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract).
Yan DaiQiwen CuiSimon S. DuPublished in: COLT (2024)
Keyphrases
- extended abstract
- function approximation
- sample complexity
- reinforcement learning algorithms
- reinforcement learning
- learning problems
- function approximators
- learning tasks
- special case
- temporal difference
- learning algorithm
- upper bound
- temporal difference learning
- lower bound
- model free
- supervised learning
- radial basis function
- active learning
- sample size
- training examples
- neural network
- data sets
- data mining