Entropy rate of continuous-state hidden Markov chains.
Guangyue HanBrian H. MarcusPublished in: ISIT (2010)
Keyphrases
- markov chain
- continuous state
- finite state
- state dependent
- steady state
- state space
- partially observable markov decision processes
- random walk
- monte carlo
- reinforcement learning
- robot navigation
- transition probabilities
- markov model
- stationary distribution
- action space
- weighted sums
- information theory
- markov decision processes
- probabilistic automata
- average cost
- machine learning
- state transition
- optimal policy
- non stationary
- relative entropy