Minimax redundancy for Markov chains with large state space.
Kedar Shriram TatwawadiJiantao JiaoTsachy WeissmanPublished in: CoRR (2018)
Keyphrases
- markov chain
- state space
- steady state
- finite state
- transition probabilities
- reinforcement learning
- dynamic programming
- transition matrix
- monte carlo
- markov decision processes
- state variables
- monte carlo method
- random walk
- monte carlo simulation
- markov model
- optimal policy
- stochastic process
- markov processes
- markov process
- search space
- stationary distribution
- dynamical systems
- evaluation function
- belief state
- game tree
- state transition
- probability distribution
- probabilistic automata
- higher order
- algo rithm