Coordinating SON instances: Reinforcement learning with distributed value function.
Ovidiu IacoboaieaBerna SayraçSana Ben JemaaPascal BianchiPublished in: PIMRC (2014)
Keyphrases
- objective function
- reinforcement learning
- multi agent
- function approximators
- cooperative
- function approximation
- distributed systems
- cooperative multi agent systems
- computer networks
- training instances
- computing environments
- reinforcement learning methods
- neural network
- learning problems
- randomly generated
- autonomous agents
- multi agent systems
- control policy
- multi agent reinforcement learning
- transition model
- learning algorithm