Throughput Maximization for Polar Coded IR-HARQ Using Deep Reinforcement Learning.
Gengxin QiuMing-Min ZhaoMing LeiMinjian ZhaoPublished in: PIMRC (2020)
Keyphrases
- reinforcement learning
- information retrieval
- response time
- function approximation
- objective function
- state space
- markov decision processes
- model free
- information retrieval systems
- evaluation measures
- fourier transform
- optimal policy
- rotation invariant
- retrieval model
- temporal difference
- polar coordinates
- robotic control
- retrieval effectiveness
- multi agent
- text retrieval
- transfer learning
- supervised learning
- frequency domain
- deep learning
- distributed information retrieval
- transition model
- search engine