Backscatter-Assisted Computation Offloading for Energy Harvesting IoT Devices via Policy-based Deep Reinforcement Learning.
Yutong XieZhengzhuo XuYuxing ZhongJing XuShimin GongYi WangPublished in: ICCC Workshops (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- mobile devices
- markov decision process
- markov decision problems
- action selection
- partially observable environments
- markov decision processes
- policy gradient
- reinforcement learning problems
- cross section
- reinforcement learning algorithms
- reward function
- action space
- function approximation
- function approximators
- temporal difference
- neural network
- decision problems
- energy consumption
- management system
- learning process
- control policy
- approximate dynamic programming
- actor critic
- state and action spaces
- partially observable domains
- policy iteration
- partially observable
- state space
- infinite horizon
- rl algorithms
- control policies
- mobile computing
- embedded systems
- evaluation function
- energy minimization
- transition model
- cloud computing
- digital libraries
- multi agent
- machine learning