Optimizing Degree Distributions of LT-based Codes with Deep Reinforcement Learning.
Yehor SavchenkoYi LiuPublished in: INFOCOM Workshops (2019)
Keyphrases
- reinforcement learning
- power law
- probability distribution
- function approximation
- multi agent
- temporal difference learning
- error correction
- optimal policy
- random variables
- machine learning
- heavy tailed
- model free
- learning problems
- graphical models
- joint distribution
- multi class
- temporal difference
- learning process
- reinforcement learning algorithms
- learning algorithm
- neural network
- error correcting codes
- multi agent reinforcement learning
- policy search