Task Offloading with Power Control for Mobile Edge Computing Using Reinforcement Learning-Based Markov Decision Process.
Bingxin ZhangGuopeng ZhangWeice SunKun YangPublished in: Mob. Inf. Syst. (2020)
Keyphrases
- markov decision process
- reinforcement learning
- power control
- state space
- markov decision processes
- optimal policy
- resource management
- temporal difference learning
- policy iteration
- infinite horizon
- power consumption
- action space
- multi hop
- wireless mesh networks
- mobile devices
- initial state
- transition probabilities
- mobile phone
- dynamic programming
- energy efficient
- wireless networks
- reinforcement learning algorithms
- optimal control
- mobile users
- cognitive radio
- reward function
- learning algorithm
- smart phones
- state variables
- mobile applications
- sufficient conditions
- markov chain
- linear programming