Minimax Redundancy for Markov Chains with Large State Space.
Kedar TatwawadiJiantao JiaoTsachy WeissmanPublished in: ISIT (2018)
Keyphrases
- markov chain
- state space
- steady state
- markov decision processes
- finite state
- reinforcement learning
- transition probabilities
- monte carlo
- markov process
- random walk
- dynamic programming
- markov model
- monte carlo simulation
- state variables
- monte carlo method
- stationary distribution
- dynamical systems
- optimal policy
- stochastic process
- markov processes
- transition matrix
- initial state
- evaluation function
- game tree
- confidence intervals
- particle filter
- state transition
- reward function