Distributed UAV-BSs Trajectory Optimization for User-Level Fair Communication Service With Multi-Agent Deep Reinforcement Learning.
Zhenquan QinZhonghao LiuGuangjie HanChuan LinLinlin GuoLing XiePublished in: IEEE Trans. Veh. Technol. (2021)
Keyphrases
- multi agent
- reinforcement learning
- fully distributed
- cooperative
- distributed control
- communication overhead
- end users
- agent communication
- communication cost
- multi agent environments
- multi agent systems
- user interface
- function approximation
- physical space
- distributed systems
- remote sites
- multi agent architecture
- state space
- multiagent systems
- learning agents
- user requests
- multimedia communication
- information dissemination
- application level
- multi agent coordination
- single agent
- user interaction
- blind source separation
- computing environments
- communication networks
- computer networks
- relevance feedback
- peer to peer
- service providers
- intelligent agents
- markov decision processes
- user satisfaction
- trajectory data
- loosely coupled
- machine learning
- web services
- short messages
- path planning
- principal component analysis
- multi party
- reinforcement learning algorithms