Reinforcement Learning Optimized Throughput for 5G Enhanced Swarm UAS Networking.
Jian WangYongxin LiuShuteng NiuHoubing SongPublished in: ICC (2021)
Keyphrases
- reinforcement learning
- function approximation
- response time
- swarm intelligence
- distributed computing
- particle swarm optimization
- reinforcement learning algorithms
- peer to peer
- optimal policy
- markov decision processes
- multi agent
- model free
- optimal control
- action selection
- temporal difference
- learning process
- transfer learning
- learning algorithm
- search space
- real robot
- buffer size
- channel capacity