Markov chain sparsification with independent sets for approximate value iteration.
Eduardo PavezNicolò MichelusiAamir AnisUrbashi MitraAntonio OrtegaPublished in: Allerton (2015)
Keyphrases
- markov chain
- approximate value iteration
- steady state
- finite state
- monte carlo
- random walk
- monte carlo method
- transition probabilities
- markov model
- state space
- stationary distribution
- fixed point
- temporal difference learning
- least squares
- transition matrix
- situation calculus
- reinforcement learning
- function approximation
- evaluation function