STDPG: A Spatio-Temporal Deterministic Policy Gradient Agent for Dynamic Routing in SDN.
Juan ChenZhiwen XiaoHuanlai XingPenglin DaiShouxi LuoMuhammad Azhar IqbalPublished in: CoRR (2020)
Keyphrases
- dynamic routing
- policy gradient
- single agent
- state action
- multi agent
- multi agent systems
- load balancing
- multiple agents
- function approximation
- intelligent agents
- mobile agents
- reinforcement learning
- gradient method
- decision problems
- agent technology
- heavy traffic
- image sequences
- travel time
- dynamic environments
- asymptotically optimal
- optimal control
- markov decision process
- approximation methods
- evolutionary algorithm
- search space
- genetic algorithm