Reinforcement Learning for Nested Polar Code Construction.
Lingchen HuangHuazi ZhangRong LiYiqun GeJun WangPublished in: GLOBECOM (2019)
Keyphrases
- reinforcement learning
- function approximation
- source code
- rotation invariant
- fourier transform
- construction process
- frequency domain
- reinforcement learning algorithms
- state space
- databases
- real time
- multi agent
- markov decision processes
- policy search
- temporal difference
- model free
- learning problems
- optimal policy
- supervised learning
- learning process
- web services
- machine learning
- data mining