A Multi-Agent Policy-Gradient Approach to Network Routing.
Nigel TaoJonathan BaxterLex WeaverPublished in: ICML (2001)
Keyphrases
- monte carlo
- network routing
- policy gradient
- multi agent
- single agent
- reinforcement learning
- dynamic optimization
- routing algorithm
- markov chain
- function approximation
- multi agent systems
- partially observable markov decision processes
- reinforcement learning algorithms
- multiple agents
- gradient method
- temporal difference
- approximation methods
- optimal control
- state space
- learning algorithm
- model free
- genetic algorithm
- dynamic environments
- state action
- artificial neural networks
- optimal solution