Computing the Feedback Capacity of Finite State Channels using Reinforcement Learning.
Ziv AharoniOron SabagHaim H. PermuterPublished in: ISIT (2019)
Keyphrases
- finite state
- markov decision processes
- reinforcement learning
- optimal policy
- continuous state
- markov chain
- policy iteration algorithm
- policy iteration
- action sets
- model checking
- state space
- reinforcement learning algorithms
- partially observable markov decision processes
- average cost
- machine learning
- function approximation
- dynamic programming
- tree automata
- context free
- partially observable
- infinite horizon
- vector quantizer
- decision problems
- markov decision process
- relevance feedback
- action selection
- long run