Computing the Feedback Capacity of Finite State Channels using Reinforcement Learning.
Ziv AharoniOron SabagHaim Henri PermuterPublished in: CoRR (2020)
Keyphrases
- finite state
- markov decision processes
- reinforcement learning
- optimal policy
- continuous state
- markov chain
- action sets
- policy iteration algorithm
- model checking
- partially observable markov decision processes
- state space
- policy iteration
- reinforcement learning algorithms
- transition systems
- context free
- infinite horizon
- average cost
- tree automata
- finite state transducers
- continuous time bayesian networks
- learning algorithm
- average reward
- optimal control
- function approximation
- decision problems
- relevance feedback
- dynamic programming
- machine learning
- partially observable
- multi agent
- continuous time markov process