Optimal Transport for Stationary Markov Chains via Policy Iteration.
Kevin O'ConnorKevin McGoffAndrew B. NobelPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- markov chain
- policy iteration
- sample path
- finite state
- average reward
- markov decision processes
- steady state
- state space
- transition probabilities
- markov processes
- markov model
- average cost
- optimal policy
- random walk
- stationary distribution
- monte carlo
- probabilistic automata
- reinforcement learning
- least squares
- model free
- stochastic process
- dynamic programming
- optimal control
- markov decision process
- non stationary
- asymptotic analysis
- transition matrix
- long run
- fixed point
- optimal solution
- infinite horizon
- temporal difference
- linear program