Attention-Shared Multi-Agent Actor-Critic-Based Deep Reinforcement Learning Approach for Mobile Charging Dynamic Scheduling in Wireless Rechargeable Sensor Networks.
Chengpeng JiangZiyang WangShuai ChenJinglin LiHaoran WangJinwei XiangWendong XiaoPublished in: Entropy (2022)
Keyphrases
- sensor networks
- reinforcement learning
- actor critic
- dynamic scheduling
- network connectivity
- multi agent
- mobile wireless
- mobile nodes
- temporal difference
- wireless sensor networks
- policy gradient
- mobile networks
- reinforcement learning algorithms
- mobile devices
- visual sensor networks
- base station
- flexible manufacturing systems
- mobile sensor networks
- approximate dynamic programming
- sensor nodes
- function approximation
- process planning
- sensor data
- optimal control
- mobile users
- state space
- wireless networks
- wireless communication
- machine learning
- learning algorithm
- optimal policy
- multi hop
- data streams
- policy iteration
- neuro fuzzy
- model free
- single agent
- partially observable markov decision processes
- routing protocol
- energy consumption
- rl algorithms
- markov decision processes
- manufacturing systems
- action selection
- multi agent systems
- gradient method
- ad hoc networks
- mobile ad hoc networks
- convergence rate
- function approximators
- evaluation function