MARTO: A Multi-agent Deep Reinforcement Learning Based Online Topology Optimization Scheme for Wireless Sensor Network.
Jiangong ZhengXiaotong GuoJianxin LiaoChao SunTongyu SongJing RenPing ZhangSiyang LiuPublished in: ICCT (2022)
Keyphrases
- optimization scheme
- reinforcement learning
- multi agent
- wireless sensor networks
- balancing exploration and exploitation
- cooperative
- multi agent reinforcement learning
- online learning
- multi agent systems
- dynamic programming
- single agent
- function approximation
- real time
- machine learning
- reinforcement learning agents
- multiagent systems
- topology control
- state space
- optimal policy
- multi agent environments
- learning agents
- reinforcement learning algorithms
- temporal difference
- action selection
- energy consumption
- sensor networks
- reinforcement learning methods
- learning classifier systems
- energy efficient
- partial differential equations
- traffic signal control
- markov decision processes