Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation.
Thinh T. DoanSiva Theja MaguluriJustin RombergPublished in: CoRR (2019)
Keyphrases
- function approximation
- temporal difference learning
- temporal difference learning algorithms
- function approximators
- reinforcement learning
- temporal difference
- radial basis function
- model free
- fixed point
- reinforcement learning algorithms
- evaluation function
- multi agent
- game playing
- dynamical systems
- learning tasks
- neural network
- training data
- decision trees
- feature selection
- machine learning