Lightweight Reinforcement Learning with State Abstraction for Dynamic Spectrum Anti-Jamming Communications.
Xin LiuXiming WangYuhua XuZhiyong DuYifan XuHao HanPublished in: WCNC (2024)
Keyphrases
- lightweight
- state abstraction
- reinforcement learning
- variable resolution
- state space
- hierarchical reinforcement learning
- reinforcement learning agents
- markov decision processes
- path finding
- communication infrastructure
- communication networks
- reinforcement learning algorithms
- dynamic environments
- function approximation
- model free
- initial state
- multi agent
- rfid tags
- development environments
- dos attacks
- machine learning
- wireless sensor networks
- learning algorithm