A Novel Two-Layered Reinforcement Learning for Task Offloading with Tradeoff between Physical Machine Utilization Rate and Delay.
Li QuanZhiliang WangFuji RenPublished in: Future Internet (2018)
Keyphrases
- reinforcement learning
- transmission rate
- real world
- trade off
- function approximation
- learning algorithm
- reinforcement learning algorithms
- robotic control
- batch processing
- optimal policy
- learning process
- multi agent
- state space
- dynamic programming
- physical objects
- temporal difference learning
- transfer learning
- flowshop
- parallel machines
- action space
- computational complexity
- bandwidth utilization