An Actor-Critic Deep Reinforcement Learning Based Computation Offloading for Three-Tier Mobile Computing Networks.
Yu LiuQimei CuiJian ZhangYu ChenYanzhao HouPublished in: WCSP (2019)
Keyphrases
- mobile computing
- actor critic
- reinforcement learning
- policy gradient
- mobile devices
- wireless networks
- temporal difference
- optimal control
- approximate dynamic programming
- reinforcement learning algorithms
- context aware
- function approximation
- mobile users
- neuro fuzzy
- data management
- gradient method
- policy iteration
- wireless communication
- mobile agents
- ubiquitous computing
- data collection
- markov decision processes
- distributed systems
- model free
- computing environments
- policy gradient methods
- dynamic programming
- transfer learning
- multi agent
- network structure
- learning algorithm
- step size
- mobile technologies
- mobile applications
- wireless sensor networks
- learning process
- temporal difference learning
- rl algorithms
- database systems
- artificial intelligence