Constructing (Bi)similar finite state abstractions using asynchronous l-complete approximations.

Anne-Kathrin Schmuck Jörg Raisch

Published in: CDC (2014)

Keyphrases

finite state
markov chain
markov decision processes
model checking
business intelligence
vector quantizer
optimal policy
partially observable markov decision processes
tree automata
machine learning
policy iteration
context free
action sets
learning algorithm
finite state transducers