A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits.
Vrettos MoulosPublished in: ISIT (2020)
Keyphrases
- finite state
- markov chain
- steady state
- monte carlo
- markov model
- random walk
- transition probabilities
- markov process
- stationary distribution
- state space
- continuous state
- stochastic process
- markov processes
- transition matrix
- average cost
- markov chain monte carlo
- partially observable markov decision processes
- confidence intervals