Near-Optimal Interdiction of Factored MDPs.

Swetasudha Panda Yevgeniy Vorobeychik

Published in: UAI (2017)

Keyphrases

factored mdps
markov decision processes
context specific
state space
algebraic decision diagrams
approximate dynamic programming
linear program
stochastic processes
basis functions
dynamic programming
general purpose
markov decision problems
markov chain
random walk
optimal policy
policy iteration