Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation.
Xingang GuoBin HuPublished in: CoRR (2022)
Keyphrases
- function approximation
- temporal difference learning
- estimation error
- temporal difference learning algorithms
- function approximators
- reinforcement learning
- temporal difference
- radial basis function
- learning tasks
- game playing
- covariance matrix
- fixed point
- evaluation function
- reinforcement learning algorithms
- model free
- multi agent
- sufficient conditions
- learning process