Feedback Capacity of Ising Channels With Large Alphabet via Reinforcement Learning.
Ziv AharoniOron SabagHaim H. PermuterPublished in: IEEE Trans. Inf. Theory (2022)
Keyphrases
- reinforcement learning
- channel state information
- markov random field
- usage statistics
- multi channel
- model free
- pattern matching
- function approximation
- user feedback
- markov decision processes
- relevance feedback
- e learning
- optimal control
- state space
- multi agent reinforcement learning
- multi agent
- learning algorithm
- wireless networks
- robotic control
- policy search
- visual feedback
- reinforcement learning algorithms
- temporal difference
- communication channels
- neural network
- supervised learning
- transfer learning
- monte carlo