Mean Field Reinforcement Learning Based Anti-Jamming Communications for Ultra-Dense Internet of Things in 6G.
Ximing WangYuhua XuJin ChenChunguo LiXin LiuDianxiong LiuYifan XuPublished in: WCSP (2020)
Keyphrases
- reinforcement learning
- high speed
- markov random field
- multi agent
- key technologies
- function approximation
- mobile devices
- learning algorithm
- machine learning
- reinforcement learning algorithms
- model free
- markov decision processes
- markov networks
- belief networks
- communication systems
- statistical mechanics
- free energy
- linear complexity
- state space
- bayesian inference
- ubiquitous computing
- closed form
- temporal difference
- em algorithm
- function approximators
- communication channels
- transfer learning
- physical world
- optimal policy
- stereo correspondence
- action space
- maximum likelihood