Multi-agent temporal-difference learning with linear function approximation: Weak convergence under time-varying network topologies.
Milos S. StankovicSrdjan S. StankovicPublished in: ACC (2016)
Keyphrases
- function approximation
- temporal difference learning
- network topologies
- temporal difference learning algorithms
- reinforcement learning
- multi agent
- function approximators
- network topology
- temporal difference
- model free
- learning tasks
- radial basis function
- fixed point
- evaluation function
- neural network
- network structure
- convergence rate
- state space
- action selection
- single agent