Scheduling for Mobile Edge Computing With Random User Arrivals - An Approximate MDP and Reinforcement Learning Approach.
Shanfeng HuangBojie LvRui WangKaibin HuangPublished in: IEEE Trans. Veh. Technol. (2020)
Keyphrases
- reinforcement learning
- markov decision processes
- optimal policy
- markov decision process
- state space
- user interface
- mobile devices
- dynamic programming
- mobile phone
- factored mdps
- policy evaluation
- scheduling algorithm
- user interaction
- linear program
- finite state
- reward function
- policy iteration
- utility function
- scheduling problem
- user experience
- linear programming
- action space
- reinforcement learning algorithms
- partially observable
- edge detection
- recommender systems
- state dependent
- function approximation
- user model
- learning algorithm
- mobile learning