Temporal Difference Learning in Network Routing.
Reid BroadbentCasey T. DeccioMark J. ClementPublished in: Communications in Computing (2004)
Keyphrases
- temporal difference learning
- network routing
- function approximation
- dynamic optimization
- fixed point
- evaluation function
- reinforcement learning
- game playing
- routing algorithm
- temporal difference
- reinforcement learning algorithms
- markov decision process
- gaussian process
- support vector machine
- nature inspired
- ant colony optimisation
- monte carlo
- ant colony optimization
- objective function
- decision making