TITLE     : Policy learning for time-bounded reachability in continuous-time Markov decision processes via doubly-stochastic gradient ascent
AUTHOR(S) : Bartocci E, Bortolussi L, Brazdil T, Milios D, Sanguinetti G
TYPE      : Conference article
YEAR      : 2016
CODE      : 424323

*** DO NOT EDIT THIS FILE ***