Enhanced Pub/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning.
Carlos E. ArrudaPedro F. MoraesNazim AgoulmineJoberto S. B. MartinsPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- temporal difference
- function approximators
- temporal difference learning
- state space
- management system
- real time
- learning algorithm
- multi agent
- communication systems
- supervised learning
- data analysis
- rl algorithms
- dynamic programming
- traffic flow
- single agent
- reward function
- big data
- network traffic
- optimal policy
- cloud computing
- traffic control
- fixed point
- markov decision processes
- transfer learning
- policy iteration
- publish subscribe
- reinforcement learning methods
- content based publish subscribe
- communication networks
- eligibility traces
- action selection
- context aware
- machine learning