Optimal Transport for Stationary Markov Chains via Policy Iteration.
Kevin O'ConnorKevin McGoffAndrew B. NobelPublished in: CoRR (2020)
Keyphrases
- markov chain
- finite state
- sample path
- policy iteration
- average reward
- markov decision processes
- steady state
- state space
- random walk
- optimal policy
- average cost
- non stationary
- optimal control
- transition probabilities
- markov model
- stationary distribution
- reinforcement learning
- long run
- monte carlo
- dynamic programming
- stochastic process
- markov processes
- probabilistic automata
- model free
- markov decision process
- state dependent
- asymptotic analysis
- transition matrix
- confidence intervals
- dynamical systems
- model checking
- learning algorithm