First-Hitting Times for Finite State Spaces.

Timo Kötzing Martin S. Krejca

Published in: PPSN (2) (2018)

Keyphrases

finite state
markov chain
markov decision processes
optimal policy
model checking
markov processes
transition systems
state space
average cost
partially observable markov decision processes
vector quantizer
information retrieval
reinforcement learning
context free
continuous time bayesian networks